INDEX

Explanations

key phrases and descriptors highlighting various attributes or qualities

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

lep

-0.16

wil

-0.15

-0.14

-0.13

Tou

-0.13

á»«a

-0.13

arel

-0.13

tid

-0.13

Ð¾Ð´Ñĸ

-0.13

anked

-0.13

POSITIVE LOGITS

KIT

0.15

subclass

0.14

artz

0.14

endor

0.14

 battery

0.14

ogle

0.13

á»ģ

0.13

ita

0.13

ikk

0.13

WebKit

0.13

Activations Density 0.161%

key phrases and descriptors highlighting various attributes or qualities

No Comments

No Known Activations