INDEX

Explanations

references to corporate entities and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 âĶľ

-0.12

 Tham

-0.12

Ã¡vÄĽ

-0.11

 Lambert

-0.11

 okol

-0.11

STITUTE

-0.11

composed

-0.10

Ngb

-0.10

Gib

-0.10

 mixed

-0.10

POSITIVE LOGITS

ãģ«ãģ¨

0.15

oenix

0.14

flater

0.13

exels

0.13

ÂŃi

0.13

okrat

0.13

icros

0.12

achuset

0.12

Ã©gor

0.12

à¤¹à¤²

0.12

Activations Density 1.355%

references to corporate entities and their activities

No Comments

No Known Activations