INDEX

Explanations

instances of the word "more" and its variations, indicating a focus on quantity and comparison

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

æĽ´å¤ļ

-0.20

 anymore

-0.17

 otherwise

-0.17

visor

-0.16

 further

-0.16

ikel

-0.15

 Ø¯ÛĮÚ¯Ø±

-0.15

ssh

-0.15

 OTHERWISE

-0.15

ÑģÑı

-0.14

POSITIVE LOGITS

 than

0.57

-than

0.45

than

0.43

 THAN

0.36

Than

0.36

 Than

0.35

_than

0.35

 niÅ¼

0.31

 Ã¤n

0.30

 importantly

0.27

Activations Density 0.215%

instances of the word "more" and its variations, indicating a focus on quantity and comparison

No Comments

No Known Activations