INDEX

Explanations

references to authors and their works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Edition

-0.17

Edition

-0.17

 edition

-0.15

_MUX

-0.14

um

-0.14

krom

-0.14

 ØŃÙĬ

-0.14

lez

-0.14

umo

-0.13

umph

-0.13

POSITIVE LOGITS

obot

0.15

irling

0.14

arken

0.13

semicolon

0.13

atu

0.13

aging

0.13

ousedown

0.13

olarity

0.13

ocom

0.13

rollo

0.13

Activations Density 0.018%

references to authors and their works

No Comments

No Known Activations