INDEX

Explanations

references to prisoners or imprisonment

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

 serialVersionUID

-0.15

 grave

-0.14

 Nicholson

-0.14

adolu

-0.14

lej

-0.14

}elseif

-0.14

POSITIVE LOGITS

orado

0.17

uty

0.15

ATURE

0.15

annies

0.15

 diá»ĩn

0.14

ature

0.14

alem

0.14

olas

0.14

 dent

0.14

umbn

0.14

Activations Density 0.004%

references to prisoners or imprisonment

No Comments

No Known Activations