INDEX

Explanations

dialogue and conversational phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 themselves

-0.19

auer

-0.19

-0.17

 há»į

-0.14

å¥¹ä»¬

-0.14

[s

-0.14

:[[

-0.14

”?

-0.14

ãģłãģĳãģ©

-0.13

 -↵

-0.13

POSITIVE LOGITS

~,

0.22

ah

0.22

 your

0.19

 miss

0.18

 Miss

0.18

~-

0.17

 Older

0.16

you

0.16

your

0.16

ãĢľ

0.16

Activations Density 0.049%

dialogue and conversational phrases

No Comments

No Known Activations

dialogue and conversational phrases

No Comments

No Known Activations