INDEX

Explanations

variations of the word "walk" and related forms, including different contexts and types of participation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

os

-0.17

ebi

-0.16

PHA

-0.15

 Bien

-0.14

'gc

-0.14

ondo

-0.14

oslav

-0.14

Ð±Ñĸ

-0.14

ysl

-0.14

 Reeves

-0.14

POSITIVE LOGITS

ä¸ĸ

0.18

ioned

0.17

æĻ®éĢļ

0.16

Ø§Ø¸

0.16

olia

0.15

_STANDARD

0.15

.fin

0.15

ventional

0.14

imeline

0.14

Activations Density 0.169%

variations of the word "walk" and related forms, including different contexts and types of participation

No Comments

No Known Activations