INDEX

Explanations

expressions of interest or perception of something as appealing

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

tera

-0.15

ful

-0.15

 Bott

-0.14

Pok

-0.14

edith

-0.14

 Thornton

-0.14

ÅĻÃŃ

-0.14

 McCabe

-0.13

foon

-0.13

POSITIVE LOGITS

 familiar

0.20

Fam

0.16

ãĥ¼ãĥľ

0.16

amiliar

0.16

seau

0.15

mouth

0.14

Ð»Ð¸Ð¼

0.14

ë¥ĺ

0.14

rait

0.14

Sus

0.14

Activations Density 0.037%

expressions of interest or perception of something as appealing

No Comments

No Known Activations

expressions of interest or perception of something as appealing

No Comments

No Known Activations