INDEX

Explanations

references to programming concepts and structures

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

gra

-0.15

ici

-0.14

py

-0.14

py

-0.14

ÄĽÅĻ

-0.14

äº¤æµģ

-0.13

icl

-0.13

vil

-0.13

à¸§à¸¥

-0.13

itia

-0.13

POSITIVE LOGITS

unma

0.17

 Ø¨ÙĪØ§Ø¨Ø©

0.15

nen

0.14

igans

0.14

 Â«

0.13

andal

0.13

leck

0.13

unately

0.13

ussions

0.13

ongyang

0.13

Activations Density 0.147%

references to programming concepts and structures

No Comments

No Known Activations