INDEX

Explanations

mentions of "Camp" or related terms indicating various camp settings or activities

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

zier

-0.18

åķª

-0.15

aten

-0.15

anke

-0.15

ropic

-0.15

imity

-0.15

uby

-0.15

earable

-0.15

urm

-0.14

zet

-0.14

POSITIVE LOGITS

ground

0.33

bell

0.33

site

0.30

grounds

0.29

agne

0.26

aigned

0.24

agn

0.24

fire

0.24

fires

0.23

aign

0.22

Activations Density 0.007%

mentions of "Camp" or related terms indicating various camp settings or activities

No Comments

No Known Activations