INDEX

Explanations

phrases related to injuries and accident descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ubar

-0.15

edor

-0.15

wap

-0.15

 ÑĤÑĢÐ°Ð½

-0.15

à¤®à¤¨

-0.14

 mouths

-0.14

illez

-0.14

argin

-0.14

 tang

-0.13

\Security

-0.13

POSITIVE LOGITS

 injury

0.52

 injured

0.47

 injuries

0.47

 Injury

0.45

spr

0.36

 injuring

0.36

inj

0.30

ä¼¤

0.30

 hurt

0.29

Spr

0.29

Activations Density 0.448%

phrases related to injuries and accident descriptions

No Comments

No Known Activations

phrases related to injuries and accident descriptions

No Comments

No Known Activations