INDEX

Explanations

references to research results or discoveries

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

istance

-0.17

aver

-0.16

outer

-0.15

undle

-0.15

utzer

-0.15

untime

-0.15

alf

-0.14

Ã¡l

-0.14

uff

-0.14

innen

-0.14

POSITIVE LOGITS

ourg

0.18

æ£ļ

0.15

urst

0.15

Å¡ti

0.14

«ĺ

0.14

ERGE

0.14

ChildIndex

0.14

ilden

0.14

/request

0.14

NEL

0.14

Activations Density 0.006%

references to research results or discoveries

No Comments

No Known Activations