INDEX

Explanations

phrases related to expressions of dissatisfaction or criticism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

tle

-0.14

usercontent

-0.14

AppBar

-0.14

ÅĻeh

-0.14

Ãłm

-0.14

chet

-0.13

gary

-0.13

isory

-0.13

ÐµÐ»Ð¸Ðº

-0.13

.Interop

-0.13

POSITIVE LOGITS

ä¸ĺ

0.17

eries

0.15

ersen

0.14

SO

0.14

aders

0.14

ayah

0.14

Woj

0.13

online

0.13

adera

0.13

unday

0.13

Activations Density 0.209%

phrases related to expressions of dissatisfaction or criticism

No Comments

No Known Activations