INDEX

Explanations

specific nouns relating to structures, packages, and physical objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

eper

-0.16

acher

-0.16

çĮ®

-0.15

akes

-0.15

aran

-0.15

 requestData

-0.14

 involved

-0.14

 åĽ

-0.14

irth

-0.14

uin

-0.14

POSITIVE LOGITS

©

0.16

ëŀĮ

0.15

iku

0.14

URA

0.14

flip

0.14

raÄį

0.14

lish

0.13

imson

0.13

ovala

0.13

acomment

0.13

Activations Density 0.326%

specific nouns relating to structures, packages, and physical objects

No Comments

No Known Activations