INDEX

Explanations

instances of the word "on."

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

/by

-0.18

/from

-0.18

cul

-0.17

duct

-0.16

Ð¾Ð»ÑĮÐ½Ð¾

-0.16

ducted

-0.15

clusions

-0.15

ì§ľ

-0.15

gos

-0.14

clarations

-0.14

POSITIVE LOGITS

 balance

0.28

 average

0.27

ward

0.27

 closer

0.26

 paper

0.26

top

0.26

 reflection

0.23

average

0.22

 rare

0.22

 thing

0.20

Activations Density 0.069%

instances of the word "on."

No Comments

No Known Activations