INDEX

Explanations

citations and references to source material

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

orough

-0.15

tz

-0.15

 Manus

-0.14

Wit

-0.14

cripts

-0.14

éĩ

-0.14

ÏģÎ¿Ïį

-0.14

æĽ

-0.13

 afford

-0.13

POSITIVE LOGITS

 adapted

0.40

adapt

0.37

 courtesy

0.37

 Adapt

0.36

taken

0.33

 taken

0.30

(Source

0.30

 source

0.29

 Source

0.28

 adaptation

0.28

Activations Density 0.269%

citations and references to source material

No Comments

No Known Activations