INDEX

Explanations

references to organizations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ãģķãģ¾

-0.16

æĺĩ

-0.15

vara

-0.14

xic

-0.14

Î¹ÏĥÎ¼

-0.14

ccione

-0.14

viron

-0.14

rypt

-0.14

Ø³Ø§Ø¨

-0.13

ivan

-0.13

POSITIVE LOGITS

eh

0.16

esser

0.15

uges

0.14

ehr

0.14

argar

0.14

achi

0.14

Ð²ÐµÑĢ

0.14

 Incident

0.13

lass

0.13

Activations Density 0.102%

references to organizations and institutions

No Comments

No Known Activations