INDEX

Explanations

phrases related to visual observations and descriptions of attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

íĸ¥

-0.15

luet

-0.15

 mekt

-0.15

ÙĬØ§

-0.14

usercontent

-0.14

alat

-0.14

imas

-0.14

etine

-0.14

overy

-0.13

antz

-0.13

POSITIVE LOGITS

 sculpt

0.23

 artic

0.22

 Sculpt

0.19

 pose

0.19

 posed

0.17

peg

0.17

 Excell

0.16

 Pose

0.16

alt

0.16

peg

0.16

Activations Density 0.001%

phrases related to visual observations and descriptions of attributes

No Comments

No Known Activations