INDEX

Explanations

references to family-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 quot

-0.16

uto

-0.15

inar

-0.15

issor

-0.15

ylene

-0.15

quot

-0.15

flix

-0.14

inos

-0.14

ilm

-0.14

elow

-0.14

POSITIVE LOGITS

oux

0.15

adero

0.14

arring

0.14

obel

0.14

amu

0.14

orida

0.13

 ÑģÐ²Ð¸

0.13

éŁ³æ¥½

0.13

shal

0.13

Ð¼ÐµÑĩ

0.13

Activations Density 0.005%

references to family-related terms

No Comments

No Known Activations