INDEX

Explanations

product specifications and requirements

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

RING

-0.16

èĬĤ

-0.15

Tube

-0.15

nez

-0.14

_COMPILE

-0.14

æ²¢

-0.14

 compact

-0.14

 Sadd

-0.14

ç¯Ģ

-0.14

urdy

-0.14

POSITIVE LOGITS

 peel

0.34

 stick

0.32

 Stick

0.32

 Peel

0.31

 stuck

0.29

Stick

0.29

 adhesive

0.29

 sticking

0.29

stick

0.28

 sticky

0.28

Activations Density 0.040%

product specifications and requirements

No Comments

No Known Activations