INDEX

Explanations

high-frequency words and phrases that indicate ownership or specification in legal and formal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

SKTOP

-0.16

Ĺi

-0.15

Tes

-0.14

rov

-0.14

&E

-0.14

unker

-0.13

ief

-0.13

stroke

-0.13

ystone

-0.13

iano

-0.13

POSITIVE LOGITS

eller

0.16

CursorPosition

0.15

 Daly

0.14

 fringe

0.14

Ãªn

0.14

etre

0.13

ftype

0.13

æ¡ĥ

0.13

çĽŁ

0.13

ople

0.13

Activations Density 0.001%

high-frequency words and phrases that indicate ownership or specification in legal and formal contexts

No Comments

No Known Activations