INDEX

Explanations

phrases related to restrictions and regulations on public and private activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

åĿ

-0.16

immers

-0.16

oldur

-0.16

Î¼ÎŃ

-0.16

/ss

-0.15

fte

-0.15

iddles

-0.15

amen

-0.15

aug

-0.14

itches

-0.14

POSITIVE LOGITS

Ost

0.17

Weg

0.15

 Plex

0.15

 kontakt

0.15

 combined

0.14

hack

0.14

 central

0.14

 degree

0.14

Sud

0.14

Activations Density 0.012%

phrases related to restrictions and regulations on public and private activities

No Comments

No Known Activations