INDEX

Explanations

references to hardware and its related features or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

è§

-0.18

naires

-0.17

herits

-0.17

ker

-0.16

aram

-0.15

ucas

-0.15

etic

-0.15

airs

-0.15

naire

-0.14

etro

-0.14

POSITIVE LOGITS

/software

0.29

itung

0.18

igua

0.17

.hw

0.16

anguage

0.15

elig

0.14

_OC

0.14

ATAL

0.14

utral

0.14

igin

0.14

Activations Density 0.007%

references to hardware and its related features or issues

No Comments

No Known Activations