INDEX

Explanations

references to quality literature or artistic works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

bourg

-0.16

deaux

-0.16

 Famous

-0.15

 subroutine

-0.15

cone

-0.15

lobals

-0.14

zilla

-0.14

onis

-0.14

Ã²ng

-0.14

ancode

-0.13

POSITIVE LOGITS

gem

0.22

gem

0.20

Gem

0.19

 rarity

0.18

 winner

0.17

 welcome

0.17

Gem

0.17

 pleasure

0.16

 force

0.16

 feast

0.16

Activations Density 0.134%

references to quality literature or artistic works

No Comments

No Known Activations