INDEX

Explanations

references to medium-sized entities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

etik

-0.15

iaux

-0.15

phin

-0.15

 withStyles

-0.15

anter

-0.15

Ã¡o

-0.15

enames

-0.15

iger

-0.14

zen

-0.14

POSITIVE LOGITS

-sized

0.40

 sized

0.40

 Sized

0.30

-size

0.29

-term

0.28

-range

0.28

size

0.26

-large

0.25

ship

0.24

-priced

0.24

Activations Density 0.022%

references to medium-sized entities or concepts

No Comments

No Known Activations