INDEX

Explanations

references to societal issues and human rights violations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

qi

-0.16

 Ø§ÙĦØªØ³

-0.15

dez

-0.14

orb

-0.14

agraph

-0.14

quat

-0.14

 Cres

-0.14

stra

-0.14

Ð¾Ð²Ð¾

-0.14

ntl

-0.14

POSITIVE LOGITS

 poor

0.19

 towards

0.17

omanip

0.17

 others

0.16

Ã¤ch

0.16

 Others

0.15

Gle

0.15

/animate

0.15

 collateral

0.15

 women

0.14

Activations Density 0.217%

references to societal issues and human rights violations

No Comments

No Known Activations