INDEX

Explanations

questions and requests for clarification or examples

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

ick

-0.15

ruk

-0.15

aly

-0.14

 Bren

-0.14

rist

-0.14

 evid

-0.14

elli

-0.14

ip

-0.14

Helpers

-0.14

Dan

-0.14

POSITIVE LOGITS

otlin

0.18

 FORCE

0.17

 ifndef

0.17

Debe

0.16

_DECLS

0.16

DTD

0.15

--[[

0.15

midi

0.15

pez

0.15

laps

0.15

Activations Density 0.377%

questions and requests for clarification or examples

No Comments

No Known Activations