INDEX

Explanations

references to facial features and face-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

udes

-0.15

AndView

-0.15

ills

-0.15

inous

-0.15

cedure

-0.15

ieder

-0.15

#echo

-0.14

ÑıÐ·

-0.14

Ø§ÛĮØ±

-0.14

lint

-0.14

POSITIVE LOGITS

/head

0.18

less

0.16

piece

0.15

 Rooney

0.15

park

0.15

/body

0.14

(face

0.14

elf

0.14

quare

0.13

guard

0.13

Activations Density 0.025%

references to facial features and face-related topics

No Comments

No Known Activations