INDEX

Explanations

instances of characters "staring" or "looking" at something, indicating attention or observation

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

uiltin

-0.16

upil

-0.16

alim

-0.15

ubat

-0.15

ural

-0.15

upert

-0.14

isel

-0.14

å¹¹ç·ļ

-0.14

ader

-0.14

ãĥ¼ãĤ¯

-0.14

POSITIVE LOGITS

 toward

0.22

 towards

0.20

 onto

0.18

Tow

0.17

 into

0.16

 Towards

0.15

onto

0.15

 upon

0.15

 hacia

0.15

 down

0.15

Activations Density 0.091%

instances of characters "staring" or "looking" at something, indicating attention or observation

No Comments

No Known Activations