INDEX

Explanations

instances of social critique regarding norms and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ute

-0.16

ãģªãģĹ

-0.15

UTE

-0.14

tps

-0.14

uting

-0.14

otherwise

-0.14

uted

-0.14

_hz

-0.14

rub

-0.13

 behalf

-0.13

POSITIVE LOGITS

 incident

0.19

 encount

0.17

 recall

0.16

/GPL

0.15

we

0.15

Ã¾

0.15

you

0.14

 accordingly

0.14

unlink

0.14

Activations Density 0.090%

instances of social critique regarding norms and values

No Comments

No Known Activations