INDEX

Explanations

references to costumes and fancy dress items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

['__

-0.17

ragon

-0.17

	define

-0.16

estone

-0.16

stone

-0.16

Ã±ana

-0.15

 jadx

-0.15

gamber

-0.15

.TXT

-0.15

 stone

-0.14

POSITIVE LOGITS

 costumes

0.28

 costume

0.25

 props

0.21

 Costume

0.19

 Props

0.18

 cost

0.18

-cost

0.17

 dressed

0.17

uron

0.17

 kost

0.17

Activations Density 0.118%

references to costumes and fancy dress items

No Comments

No Known Activations