INDEX

Explanations

phrases indicating contrasting perspectives 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ulos

-0.17

ktor

-0.16

zew

-0.16

.nih

-0.15

ÐµÑĢÐ°ÑĤÑĥ

-0.15

leri

-0.15

ÙĥØ§ÙĨ

-0.14

istar

-0.14

à¸İ

-0.14

POSITIVE LOGITS

 couldn

0.88

couldn

0.83

 Couldn

0.78

Couldn

0.59

 could

0.23

 unable

0.23

 incapable

0.21

 nemoh

0.20

Could

0.19

 Could

0.19

Activations Density 0.152%

phrases indicating contrasting perspectives or situations

No Comments

No Known Activations