INDEX

Explanations

news articles and publication details related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 vess

-0.16

 slee

-0.16

 Prompt

-0.15

 dich

-0.15

UG

-0.15

à¸Ħà¸£

-0.14

ocket

-0.14

ugi

-0.14

éħį

-0.14

poss

-0.14

POSITIVE LOGITS

_outline

0.18

zell

0.18

strstr

0.15

adle

0.15

 strstr

0.14

 Ø§ÛĮØ³Øª

0.14

efault

0.14

ä¹ĭ

0.14

IMATION

0.14

nict

0.14

Activations Density 0.527%

news articles and publication details related to various topics

No Comments

No Known Activations

news articles and publication details related to various topics

No Comments

No Known Activations