INDEX

Explanations

references to mouth-related imagery or descriptions

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

º«

-0.15

ãĥ£

-0.15

ATRIX

-0.14

ÎŃÏģ

-0.14

calar

-0.14

utow

-0.14

 infinit

-0.14

hea

-0.14

embro

-0.14

ipar

-0.14

POSITIVE LOGITS

ful

0.34

piece

0.32

wash

0.29

water

0.28

-water

0.26

FUL

0.26

 watering

0.25

pieces

0.25

feel

0.23

guards

0.23

Activations Density 0.019%

references to mouth-related imagery or descriptions

No Comments

No Known Activations