INDEX

Explanations

references to law enforcement and police officers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ada

-0.16

iet

-0.15

å¶

-0.14

Abe

-0.14

æ¥Ń

-0.14

ADA

-0.14

ÏĨÎ±

-0.14

Din

-0.13

TH

-0.13

POSITIVE LOGITS

 Yates

0.15

pdev

0.15

enddate

0.14

istrovstvÃŃ

0.14

eos

0.14

styl

0.14

pageNumber

0.13

allest

0.13

lÃ¼k

0.13

eo

0.13

Activations Density 0.008%

references to law enforcement and police officers

No Comments

No Known Activations