INDEX

Explanations

phrases related to connection and accessibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

/vnd

-0.17

 Regents

-0.16

OTAL

-0.16

elik

-0.15

ë§ŀ

-0.14

uchi

-0.14

ÅĻ

-0.13

 Learned

-0.13

èķī

-0.13

 Rena

-0.13

POSITIVE LOGITS

 Cord

0.17

ninger

0.16

 cord

0.14

uzu

0.14

itter

0.14

 convex

0.14

ause

0.14

_mapper

0.14

 CreateMap

0.14

 onHide

0.14

Activations Density 0.002%

phrases related to connection and accessibility

No Comments

No Known Activations