INDEX

Explanations

specific dates and events

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

ç©

-0.14

Ļ¨

-0.14

ãģĭãģª

-0.14

 à¤ĩà¤¸à¤®

-0.14

èģĺ

-0.13

oret

-0.13

PEG

-0.13

ë³ĳ

-0.13

aupt

-0.12

 à¤ĩà¤¸à¤¸

-0.12

POSITIVE LOGITS

 will

0.19

will

0.17

 join

0.17

 hundreds

0.16

 representatives

0.15

 thousands

0.15

join

0.15

è¡Ĩ

0.15

 occurring

0.15

 marks

0.14

Activations Density 0.134%

specific dates and events

No Comments

No Known Activations