INDEX

Explanations

references to various associations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ramework

-0.18

agra

-0.17

inas

-0.17

.semantic

-0.16

omu

-0.15

vider

-0.15

apore

-0.15

drops

-0.15

tet

-0.14

 Guth

-0.14

POSITIVE LOGITS

isel

0.16

ilton

0.15

 Danh

0.14

udson

0.14

ãģµ

0.14

Ú©Ø´

0.14

ered

0.14

ild

0.14

ÙĦØ³

0.13

Ã¡h

0.13

Activations Density 0.021%

references to various associations and organizations

No Comments

No Known Activations