INDEX

Explanations

terms related to user interactions and feedback

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

aley

-0.16

oxic

-0.16

oso

-0.15

Ø§Ø¦ÙĬØ©

-0.14

ux

-0.14

Ð½ÑıÑĤ

-0.14

uncan

-0.14

 ustanov

-0.14

osos

-0.14

antha

-0.14

POSITIVE LOGITS

usan

0.16

affen

0.16

FieldType

0.16

 prav

0.14

bean

0.14

Äįin

0.14

Opens

0.14

Abs

0.13

rac

0.13

 loose

0.13

Activations Density 0.003%

terms related to user interactions and feedback

No Comments

No Known Activations