INDEX

Explanations

references to occupations, roles, or positions within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

eyer

-0.18

eyi

-0.16

ÐµÑĢÐº

-0.16

.har

-0.15

 Hemisphere

-0.14

oble

-0.14

anja

-0.14

ayer

-0.14

els

-0.14

linger

-0.14

POSITIVE LOGITS

æ²

0.15

ierz

0.15

ÑĪÐ°

0.15

 aspect

0.15

riage

0.15

of

0.14

Ĭ¶

0.14

gid

0.14

isha

0.14

 infix

0.14

Activations Density 0.448%

references to occupations, roles, or positions within organizations

No Comments

No Known Activations