INDEX

Explanations

phrases related to legal liability and knowledge

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

/Gate

-0.18

blas

-0.14

lÃ¡Å¡

-0.14

 ì¼ĢìĿ´

-0.14

panion

-0.14

apur

-0.14

 xÃ©t

-0.14

endra

-0.14

Ã¡bado

-0.13

Ø§Ø¦Ø±

-0.13

POSITIVE LOGITS

 knowledge

0.26

 knew

0.26

 known

0.21

 Knowledge

0.20

 reasonable

0.20

knowledge

0.19

 knowing

0.19

çŁ¥è¯Ĩ

0.17

 conhec

0.17

 reasonably

0.17

Activations Density 0.090%

phrases related to legal liability and knowledge

No Comments

No Known Activations