INDEX

Explanations

numerical specifications and measurements 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ces

-0.15

AGMA

-0.15

Î¬

-0.15

 cess

-0.14

oric

-0.14

asso

-0.14

imli

-0.14

Ð°ÑĢÐ´

-0.14

 Ellison

-0.14

ander

-0.13

POSITIVE LOGITS

/Branch

0.14

ocker

0.14

 Depends

0.14

/Internal

0.14

trys

0.14

semblies

0.13

eker

0.13

xAA

0.13

 surrounding

0.13

Activations Density 0.037%

numerical specifications and measurements in various contexts

No Comments

No Known Activations