INDEX

Explanations

names and identities of individuals or authors 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 @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Ð»Ð¾Ð¿

-0.14

Truthy

-0.14

rech

-0.14

æ¥

-0.14

åĥı

-0.14

mouseleave

-0.14

ë°ĺ

-0.14

avana

-0.14

-One

-0.14

erase

-0.13

POSITIVE LOGITS

0.16

 Gonz

0.15

bert

0.15

 alias

0.15

bral

0.14

 Barber

0.14

enville

0.14

 Reyn

0.14

Activations Density 0.007%

names and identities of individuals or authors in the text

No Comments

No Known Activations