INDEX

Explanations

instances of the word "require" and its variations indicating necessity or dependence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

reau

-0.17

enis

-0.16

-0.15

æľīéĻĲ

-0.15

illisecond

-0.14

emes

-0.14

 punch

-0.14

ilder

-0.14

emean

-0.14

POSITIVE LOGITS

edom

0.18

Ð°Ð»Ð¾Ð²

0.16

oke

0.16

[](

0.16

ëŀĳìĬ¤

0.15

*pow

0.15

/loose

0.15

uet

0.15

/xhtml

0.14

ant

0.14

Activations Density 0.035%

instances of the word "require" and its variations indicating necessity or dependence

No Comments

No Known Activations