INDEX

Explanations

words related to the concept of "extension" or "extending."

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

onth

-0.17

ily

-0.14

/swagger

-0.14

erce

-0.14

unately

-0.14

owitz

-0.14

ifications

-0.13

uze

-0.13

rint

-0.13

zcze

-0.13

POSITIVE LOGITS

(extension

0.22

 Extension

0.17

-extension

0.17

-reaching

0.17

extension

0.17

ential

0.16

å»¶

0.16

 extension

0.16

ibility

0.16

credits

0.16

Activations Density 0.060%

words related to the concept of "extension" or "extending."

No Comments

No Known Activations