INDEX

Explanations

phrases indicating a range or selection of options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 anderen

-0.16

åı¦å¤ĸ

-0.15

 åħ¶ä»ĸ

-0.15

 OTHER

-0.15

nier

-0.15

 altri

-0.14

other

-0.14

åı¦ä¸Ģ

-0.14

">ÃĹ</

-0.14

OTHER

-0.14

POSITIVE LOGITS

 simple

0.30

 humble

0.26

 smallest

0.25

simple

0.24

 simples

0.24

ç®Ģåįķ

0.23

 simplest

0.23

 small

0.22

 basic

0.21

 inception

0.21

Activations Density 0.070%

phrases indicating a range or selection of options

No Comments

No Known Activations