INDEX

Explanations

instances of author names or contributions in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

edy

-0.17

lif

-0.15

yas

-0.15

ober

-0.14

rint

-0.14

jie

-0.13

esa

-0.13

ova

-0.13

roe

-0.13

ECH

-0.13

POSITIVE LOGITS

Posts

0.17

 published

0.16

Tau

0.16

	Global

0.15

ublished

0.15

 Published

0.14

Ã¡u

0.14

Tau

0.14

ublice

0.14

ifu

0.14

Activations Density 0.015%

instances of author names or contributions in the text

No Comments

No Known Activations