INDEX

Explanations

references to employment or job roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

phet

-0.16

 itself

-0.15

ussian

-0.15

raya

-0.15

Ð¬

-0.15

å®ĥä»¬

-0.14

Ð»ÑİÐ´

-0.14

kte

-0.14

Yii

-0.14

ãģĸ

-0.14

POSITIVE LOGITS

 whom

0.28

who

0.25

who

0.20

 whose

0.19

hip

0.18

/vendors

0.17

innen

0.17

½

0.16

 McCl

0.15

estinal

0.15

Activations Density 0.102%

references to employment or job roles

No Comments

No Known Activations