INDEX

Explanations

expressions of uncertainty, doubt, and lack of knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

GS

-0.15

ucher

-0.15

 Levine

-0.15

ildo

-0.14

pliers

-0.14

antal

-0.14

 offending

-0.13

á»§ng

-0.13

Ã¼rn

-0.13

jest

-0.13

POSITIVE LOGITS

Eigen

0.17

Bai

0.16

 except

0.15

burgh

0.15

except

0.15

wald

0.15

 PRESS

0.14

ero

0.14

 hoop

0.14

_stylesheet

0.14

Activations Density 0.137%

expressions of uncertainty, doubt, and lack of knowledge

No Comments

No Known Activations