INDEX

Explanations

phrases that indicate specific contexts or environments

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

è³¢

-0.17

awns

-0.15

Ã¼ss

-0.14

é§Ĳ

-0.14

auge

-0.14

upertino

-0.13

ÙħÙĤ

-0.13

TEGER

-0.13

erm

-0.13

ableView

-0.13

POSITIVE LOGITS

 bounds

0.52

 confines

0.48

 framework

0.47

 boundaries

0.42

framework

0.41

 limits

0.39

 context

0.37

 frameworks

0.37

 walls

0.36

 scope

0.34

Activations Density 0.096%

phrases that indicate specific contexts or environments

No Comments

No Known Activations