INDEX

Explanations

HTML and navigation-related elements in the text

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

ÑħÑĥ

-0.15

äº¤

-0.15

assen

-0.14

Ð´Ð°Ð¼

-0.14

enga

-0.14

urgeon

-0.14

ternet

-0.14

ruba

-0.14

baugh

-0.13

éĢ

-0.13

POSITIVE LOGITS

Sco

0.16

Ã¼ph

0.15

icus

0.15

arith

0.14

 Stephan

0.14

anlÄ±

0.14

anz

0.14

 Curt

0.13

ATTER

0.13

ieve

0.13

Activations Density 0.007%

HTML and navigation-related elements in the text

No Comments

No Known Activations