INDEX

Explanations

instances of the word "rug" and its variations related to style and design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

chÃ©

-0.15

.mybatisplus

-0.15

itag

-0.15

hana

-0.14

Ã¶m

-0.14

crement

-0.14

 untranslated

-0.14

ãģĦãĤĭ

-0.14

ournÃ©e

-0.14

QS

-0.13

POSITIVE LOGITS

ger

0.24

anova

0.18

æŀľ

0.16

uggy

0.15

wort

0.15

ernaut

0.14

nuts

0.14

lasses

0.14

ouv

0.14

Activations Density 0.032%

instances of the word "rug" and its variations related to style and design

No Comments

No Known Activations