INDEX

Explanations

references to user support and assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 themselves

-0.19

 itself

-0.16

acro

-0.15

Äĥ

-0.14

 usted

-0.14

net

-0.14

stoff

-0.14

nb

-0.14

nya

-0.14

atti

-0.14

POSITIVE LOGITS

/us

0.27

-mÃªme

0.25

zelf

0.23

/her

0.22

SELF

0.20

åĢĳ

0.19

 guys

0.18

’re

0.17

nger

0.17

self

0.16

Activations Density 0.126%

references to user support and assistance

No Comments

No Known Activations