INDEX

Explanations

instances of the word "have" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 itself

-0.16

ungan

-0.16

Ð¾Ð½Ñĸ

-0.15

arra

-0.15

sg

-0.15

anco

-0.15

naments

-0.15

ami

-0.14

ni

-0.14

lient

-0.14

POSITIVE LOGITS

eny

0.15

iÄįky

0.14

ãĥ³ãĤ¹

0.14

´Ŀ

0.14

eki

0.14

eah

0.13

 Sheridan

0.13

 Alias

0.13

lou

0.13

urray

0.13

Activations Density 0.156%

instances of the word "have" in various contexts

No Comments

No Known Activations