INDEX

Explanations

headings and references to various forms of recognition or awards

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

arella

-0.17

Ð¸Ñī

-0.17

uese

-0.16

chedulers

-0.15

-0.14

 vegas

-0.14

urai

-0.14

Ã©rie

-0.14

-lfs

-0.14

aversable

-0.13

POSITIVE LOGITS

 Hart

0.16

edList

0.15

_DD

0.15

éĲĺ

0.14

RYPT

0.14

ope

0.14

inputEmail

0.13

ÏįÎ½

0.13

 Flint

0.13

ÄĻki

0.13

Activations Density 0.204%

headings and references to various forms of recognition or awards

No Comments

No Known Activations