INDEX

Explanations

names of people and organizations involved in discussions or reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

atel

-0.15

ixmap

-0.15

zi

-0.14

Ã¹i

-0.14

naw

-0.14

ieu

-0.14

ignon

-0.13

elian

-0.13

Ð»ÑıÐ²

-0.13

POSITIVE LOGITS

IND

0.15

lg

0.14

pha

0.14

 Moral

0.13

ion

0.13

çī

0.13

indo

0.13

ucht

0.13

èĪĪ

0.13

 couch

0.12

Activations Density 0.042%

names of people and organizations involved in discussions or reports

No Comments

No Known Activations

names of people and organizations involved in discussions or reports

No Comments

No Known Activations