INDEX

Explanations

occurrences of the word "contact."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

bery

-0.18

ISTIC

-0.15

acock

-0.15

sters

-0.15

unos

-0.14

oted

-0.14

á»Ļng

-0.14

Î´Î¹Î±

-0.14

/null

-0.14

istr

-0.14

POSITIVE LOGITS

ually

0.32

ual

0.30

 lenses

0.27

ors

0.25

ivity

0.25

UAL

0.24

 lens

0.23

 Lens

0.20

ible

0.19

less

0.19

Activations Density 0.033%

occurrences of the word "contact."

No Comments

No Known Activations