INDEX

Explanations

references to specific years and notable media releases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.31

-0.28

Û±Û¹Û¶

-0.21

-0.20

DVD

-0.17

Û±Û¹Ûµ

-0.16

 DVDs

-0.16

apesh

-0.15

Ð·Ñĥ

-0.15

phia

-0.14

POSITIVE LOGITS

0.57

 Reagan

0.44

Û±Û¹Û¸

0.42

 Thatcher

0.26

 AIDS

0.20

 Ronald

0.20

 Atari

0.18

 Exxon

0.17

 cassette

0.17

ï¼ĪæĺŃåĴĮ

0.17

Activations Density 0.309%

references to specific years and notable media releases

No Comments

No Known Activations