INDEX

Explanations

terms and phrases related to vision and visual perception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

stants

-0.17

Ð°Ð»Ð¸Ð·

-0.16

uese

-0.15

sty

-0.15

ilen

-0.15

icontrol

-0.15

ãĥ³ãĤ¿

-0.14

ichern

-0.14

 Dias

-0.14

POSITIVE LOGITS

 consect

0.17

ÏĦÎ¿Î½

0.15

_INTR

0.15

-eye

0.14

/head

0.14

oring

0.14

uf

0.14

 VÅ¡ech

0.14

æ

0.14

aset

0.14

Activations Density 0.090%

terms and phrases related to vision and visual perception

No Comments

No Known Activations