INDEX

Explanations

mentions of government positions and roles within political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ãģľ

-0.15

ges

-0.15

RAINT

-0.14

 Brewer

-0.14

oning

-0.14

 ÑĢÑĥÑĩ

-0.14

atat

-0.14

 Dund

-0.14

eper

-0.14

à¸ł

-0.14

POSITIVE LOGITS

apes

0.15

innie

0.14

elsen

0.13

_defaults

0.13

ione

0.13

 Burk

0.13

à¸²à¸£à¸ĸ

0.13

bury

0.13

phinx

0.13

Activations Density 0.081%

mentions of government positions and roles within political contexts

No Comments

No Known Activations