INDEX

Explanations

phrases indicating ownership or possession

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

these

-0.17

Ð²Ð¾ÑĢ

-0.16

 EITHER

-0.15

 THESE

-0.14

them

-0.13

uat

-0.13

uko

-0.13

_BOTH

-0.13

queda

-0.13

osto

-0.13

POSITIVE LOGITS

how

0.30

 hoping

0.29

 what

0.26

why

0.25

how

0.22

 where

0.22

 everything

0.20

 some

0.19

 links

0.19

 proof

0.18

Activations Density 0.023%

phrases indicating ownership or possession

No Comments

No Known Activations