INDEX

Explanations

references to events and schedules

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

isay

-0.16

ãģªãģ®

-0.15

inations

-0.14

áº¡ng

-0.14

 besoin

-0.14

 Must

-0.14

ä¸įåı¯

-0.14

ãģĹãģ¾

-0.14

inders

-0.14

inder

-0.14

POSITIVE LOGITS

 should

0.89

 Should

0.79

should

0.79

Should

0.75

 ought

0.69

.should

0.68

 SHOULD

0.66

 shouldn

0.64

åºĶè¯¥

0.63

_should

0.62

Activations Density 0.341%

references to events and schedules

No Comments

No Known Activations