INDEX

Explanations

references to laboratory-related terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ambda

-0.18

eous

-0.17

AZY

-0.16

_lazy

-0.16

eed

-0.15

leaf

-0.15

ERIC

-0.15

weed

-0.15

atego

-0.15

xca

-0.14

POSITIVE LOGITS

elling

0.39

rador

0.29

VIEW

0.24

rary

0.23

/lab

0.22

 coat

0.21

ellers

0.21

coat

0.20

 coats

0.20

bers

0.19

Activations Density 0.014%

references to laboratory-related terms and concepts

No Comments

No Known Activations