INDEX

Explanations

phrases related to ownership or affiliation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

loh

-0.17

icker

-0.16

IDER

-0.15

iders

-0.15

udios

-0.15

Î¼ÎŃ

-0.15

ider

-0.14

cps

-0.14

dsl

-0.14

POSITIVE LOGITS

 belong

0.19

(ed

0.18

 belonged

0.17

 belongs

0.17

ence

0.16

belongs

0.16

endir

0.15

azer

0.15

Bel

0.15

Activations Density 0.012%

phrases related to ownership or affiliation

No Comments

No Known Activations