INDEX

Explanations

names and specific references related to individuals, locations, and organizations in a political context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ï»¿using

-0.13

_Tis

-0.13

ermalink

-0.13

Periph

-0.13

_softc

-0.13

 wireType

-0.12

/MPL

-0.12

.UIManager

-0.11

ypse

-0.11

ibName

-0.11

POSITIVE LOGITS

 Ð¶Ðµ

0.14

;-

0.12

Ä±sÄ±z

0.12

Ð¼ÐµÑĩ

0.12

-but

0.12

 ãĢģ

0.12

/her

0.11

mÄĽ

0.11

/add

0.11

ASIC

0.11

Activations Density 0.873%

names and specific references related to individuals, locations, and organizations in a political context

No Comments

No Known Activations