INDEX

Explanations

references and citations 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

anie

-0.13

ÄĲT

-0.13

inen

-0.13

ansi

-0.13

 Tenant

-0.13

Î¹ÎºÎ¿Ïį

-0.13

elters

-0.13

>Type

-0.13

 Smarty

-0.12

avid

-0.12

POSITIVE LOGITS

Ñī

0.16

getDb

0.15

_Result

0.14

udge

0.14

amat

0.14

RING

0.14

DisplayStyle

0.14

ãģ¤ãģĳ

0.14

TEM

0.14

_REQUIRE

0.14

Activations Density 0.173%

references and citations in the text

No Comments

No Known Activations