INDEX

Explanations

possessive forms indicating ownership or association

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ä¸ģ

-0.15

Ã³i

-0.15

zcze

-0.15

ummer

-0.14

heimer

-0.14

.DisplayName

-0.13

StringEncoding

-0.13

ndern

-0.13

ieved

-0.13

Ð»ÑĸÐ´

-0.13

POSITIVE LOGITS

\brief

0.17

ocz

0.16

 itself

0.15

umann

0.14

ÂĢÂĢ

0.14

Â©Â©

0.14

(&_

0.14

pon

0.14

Activations Density 0.150%

possessive forms indicating ownership or association

No Comments

No Known Activations