INDEX

Explanations

phrases that reference parts or features of a whole

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

sit

-0.18

oug

-0.18

oga

-0.17

readcr

-0.15

Ã©e

-0.15

/off

-0.15

ict

-0.14

zin

-0.14

 Boone

-0.14

ÐµÐ³Ð¾Ð´

-0.14

POSITIVE LOGITS

 pieces

0.17

psilon

0.16

work

0.16

alink

0.15

 Pieces

0.15

íĴĪ

0.15

pieces

0.15

achat

0.14

ÑĩÐ°

0.14

Activations Density 0.038%

phrases that reference parts or features of a whole

No Comments

No Known Activations