INDEX

Explanations

references to young adults

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

amo

-0.15

 Acting

-0.13

Rew

-0.13

ãģ¡

-0.13

llen

-0.13

afka

-0.13

 entitled

-0.13

LocalizedMessage

-0.13

////////////////////////////////////////////////////////////////////////////////↵↵

-0.13

 Zimmer

-0.13

POSITIVE LOGITS

chwitz

0.16

odzi

0.14

eness

0.14

sons

0.14

DDL

0.14

ulse

0.14

izontally

0.14

 Spread

0.14

moz

0.14

spread

0.14

Activations Density 0.008%

references to young adults

No Comments

No Known Activations