INDEX

Explanations

numerical data, specifically related to measurements or specifications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

pez

-0.15

 âĦĸ

-0.14

 separate

-0.14

à¸ĳ

-0.14

ì§ģ

-0.14

endra

-0.13

coop

-0.13

 Daniels

-0.13

Tro

-0.13

leet

-0.13

POSITIVE LOGITS

uitka

0.15

acci

0.15

instanc

0.14

ãĥ¼ãĥĭ

0.14

etas

0.14

 onView

0.14

ForResource

0.14

SAFE

0.13

IDD

0.13

Ã³ln

0.13

Activations Density 0.254%

numerical data, specifically related to measurements or specifications in various contexts

No Comments

No Known Activations