INDEX

Explanations

political actions and statements related to legislation and regulation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

åļ

-0.16

Ð¾Ð²Ð°ÑĢÐ¸

-0.15

Unsafe

-0.14

à¹Ģà¸ķà¸£

-0.14

ÑģÑĤÑĢÑĥ

-0.14

kola

-0.13

AGMA

-0.13

BOSE

-0.13

 outs

-0.13

æ±

-0.13

POSITIVE LOGITS

0.15

ison

0.15

 command

0.14

ª

0.14

PLE

0.14

Son

0.14

iali

0.14

dsn

0.14

 himself

0.14

frey

0.14

Activations Density 0.376%

political actions and statements related to legislation and regulation

No Comments

No Known Activations