INDEX

Explanations

legal disclaimers and warnings about medical advice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ue

-0.16

hof

-0.15

LOAT

-0.15

 Bern

-0.15

son

-0.14

onio

-0.14

 glove

-0.14

 Toys

-0.14

 Negro

-0.14

POSITIVE LOGITS

iales

0.17

ãģ¾ãģ¨

0.16

igt

0.15

/cache

0.15

çħ

0.14

coc

0.14

doch

0.14

cÃŃm

0.14

ellido

0.14

orgot

0.14

Activations Density 0.036%

legal disclaimers and warnings about medical advice

No Comments

No Known Activations