INDEX

Explanations

references to specific statistical data and reports

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

gre

-0.15

TokenType

-0.14

jal

-0.14

æĿ¯

-0.14

 rejection

-0.14

ede

-0.14

 Sinn

-0.14

Ø§Ø¯ÙĬ

-0.14

ISCO

-0.14

igor

-0.13

POSITIVE LOGITS

unto

0.16

utto

0.15

oth

0.15

thag

0.14

ambi

0.14

è¨±

0.14

 chod

0.14

andra

0.14

 biÃªn

0.14

uto

0.14

Activations Density 0.243%

references to specific statistical data and reports

No Comments

No Known Activations