INDEX

Explanations

phrases indicating importance or necessity

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

isoft

-0.17

deen

-0.15

ugins

-0.14

ìĿ´íĦ°

-0.14

rieben

-0.14

.GetText

-0.14

à¸Ľà¸£à¸°à¸¡

-0.14

 Samp

-0.14

atter

-0.13

POSITIVE LOGITS

Ĵ

0.16

 kind

0.16

kind

0.15

mil

0.14

 kinds

0.14

omm

0.14

blob

0.14

ÑĤÐ¸Ðº

0.14

 sort

0.14

ÑĥÑĢÐ³

0.14

Activations Density 0.088%

phrases indicating importance or necessity

No Comments

No Known Activations