INDEX

Explanations

phrases indicating classification or evaluation of objects and concepts

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

ipes

-0.15

ppe

-0.15

abyrin

-0.15

tem

-0.15

redits

-0.15

iferay

-0.14

adows

-0.14

utoff

-0.13

inds

-0.13

agon

-0.13

POSITIVE LOGITS

azzi

0.16

enance

0.15

YL

0.14

 Provid

0.14

éĻµ

0.14

Î¼Î¯Î±

0.14

 Barbar

0.13

quals

0.13

Fair

0.13

elian

0.13

Activations Density 0.050%

phrases indicating classification or evaluation of objects and concepts

No Comments

No Known Activations