INDEX

Explanations

references to professions and roles in various contexts

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

æ¥

-0.16

$MESS

-0.15

-0.14

çīĻ

-0.14

unks

-0.14

ê½

-0.14

 moduleId

-0.13

apiro

-0.13

ruk

-0.13

Ä¢

-0.13

POSITIVE LOGITS

 John

1.23

John

1.13

 JOHN

1.08

 john

0.99

john

0.90

 ÐĶÐ¶Ð¾Ð½

0.87

 Johns

0.83

ohn

0.71

 ì¡´

0.69

 Johnston

0.65

Activations Density 0.174%

references to professions and roles in various contexts

No Comments

No Known Activations