INDEX

Explanations

connections to specific items or contributions in a broader context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-0.18

eraÃ§Ã£o

-0.17

eyim

-0.16

unsch

-0.16

 xOffset

-0.15

illions

-0.15

enÄĽ

-0.14

lot

-0.14

aller

-0.14

POSITIVE LOGITS

UID

0.19

iere

0.19

ahir

0.18

uir

0.18

Hi

0.18

uyen

0.17

imir

0.16

ulsion

0.16

hi

0.16

uso

0.15

Activations Density 0.036%

connections to specific items or contributions in a broader context

No Comments

No Known Activations