INDEX

Explanations

terms related to legal or governmental processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ab

-0.18

 lesbische

-0.17

ize

-0.16

-0.14

isz

-0.14

meer

-0.14

æıĽ

-0.14

lt

-0.14

asi

-0.14

POSITIVE LOGITS

porter

0.17

/commons

0.16

ogra

0.15

 polish

0.15

orton

0.15

nad

0.14

tsky

0.14

emy

0.14

viar

0.14

igli

0.14

Activations Density 0.198%

terms related to legal or governmental processes

No Comments

No Known Activations