INDEX

Explanations

mathematical definitions and theorems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ingen

-0.15

ÑĢÑĥÐ¶

-0.15

elin

-0.14

ilerden

-0.14

ERO

-0.14

acha

-0.13

nelle

-0.13

enek

-0.13

Ð¼ÐµÑĩ

-0.13

quam

-0.13

POSITIVE LOGITS

 note

0.17

 Rough

0.17

 inform

0.16

 Interest

0.16

Mot

0.16

 Inform

0.16

Note

0.15

 notice

0.15

 incident

0.15

 readers

0.15

Activations Density 0.094%

mathematical definitions and theorems

No Comments

No Known Activations