INDEX

Explanations

instances of the word "mark" and its variations, indicating an emphasis on the concept of marking or indicating something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

archy

-0.18

æ¢¯

-0.17

è¦

-0.16

-0.15

cci

-0.15

kowski

-0.14

ARCH

-0.14

ī

-0.14

ugi

-0.14

Äįet

-0.14

POSITIVE LOGITS

edly

0.29

eting

0.29

etable

0.25

eted

0.24

places

0.22

sm

0.22

ansas

0.22

ups

0.21

down

0.21

eters

0.21

Activations Density 0.056%

instances of the word "mark" and its variations, indicating an emphasis on the concept of marking or indicating something

No Comments

No Known Activations