INDEX

Explanations

words related to actions and relationships involving community and support

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

Å¡tÄĽ

-0.16

%B

-0.15

 Jacobs

-0.15

PÅĻed

-0.14

 Thom

-0.14

wolf

-0.14

erdale

-0.14

otts

-0.14

VÃ½

-0.14

âĢŀTo

-0.14

POSITIVE LOGITS

åĨ

0.15

annya

0.14

eme

0.14

iferay

0.14

Ø²Ùħ

0.14

wap

0.14

zell

0.13

 Ø¨ÙĨØ§

0.13

ilon

0.13

 Enumerator

0.13

Activations Density 0.015%

words related to actions and relationships involving community and support

No Comments

No Known Activations