INDEX

Explanations

references to repetition and recurrence in activities or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

auer

-0.14

_:*

-0.14

atte

-0.14

uell

-0.13

aidu

-0.13

nam

-0.13

LG

-0.13

Ã¡vÃ¡nÃŃ

-0.13

lsx

-0.13

yor

-0.13

POSITIVE LOGITS

vere

0.15

wards

0.15

 ÑħÑĥÐ´

0.15

-validator

0.14

Font

0.14

ÑĥÐ´Ð°

0.14

 calor

0.14

uten

0.13

çĽĳåĲ¬é¡µéĿ¢

0.13

ilos

0.13

Activations Density 0.134%

references to repetition and recurrence in activities or situations

No Comments

No Known Activations