INDEX

Explanations

mentions of specific places or institutions

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

osexual

-0.17

 Ð¿ÑĢÐ¾ÑĦÐµÑģÑģÐ¸Ð¾Ð½Ð°Ð»ÑĮ

-0.16

Ãªn

-0.15

zb

-0.15

 Bundle

-0.15

ewan

-0.14

ibold

-0.14

zend

-0.14

ä¿¡çĶ¨

-0.14

.asm

-0.13

POSITIVE LOGITS

iaux

0.14

ounge

0.14

 Django

0.14

ottes

0.14

 Rational

0.13

 ↵↵

0.13

umi

0.13

alse

0.13

 Lung

0.13

acion

0.13

Activations Density 0.001%

mentions of specific places or institutions

No Comments

No Known Activations