INDEX

Explanations

various forms of the verb "play" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

cci

-0.17

ska

-0.16

rees

-0.15

WRAPPER

-0.15

ighet

-0.15

/from

-0.14

stal

-0.14

mland

-0.14

ÑĢÐµÐ·

-0.14

qli

-0.14

POSITIVE LOGITS

 games

0.27

 favorites

0.24

 havoc

0.22

 cards

0.22

 dress

0.22

 tricks

0.22

 favourites

0.21

 catch

0.20

 Favorites

0.20

tug

0.19

Activations Density 0.034%

various forms of the verb "play" in different contexts

No Comments

No Known Activations