INDEX

Explanations

instances of the word "change" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

rose

-0.21

ness

-0.18

nett

-0.17

çĦ¶

-0.17

rots

-0.17

ly

-0.17

turned

-0.16

-China

-0.16

_changes

-0.16

als

-0.15

POSITIVE LOGITS

over

0.35

able

0.29

overs

0.24

/new

0.21

/update

0.20

ability

0.20

/add

0.20

cate

0.18

iator

0.18

Maker

0.17

Activations Density 0.084%

instances of the word "change" and its variations

No Comments

No Known Activations