INDEX

Explanations

elements related to programming or coding structures

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

undy

-0.17

unsch

-0.16

mani

-0.16

Mocks

-0.15

omi

-0.14

Î½Î¹Î±

-0.14

 Joint

-0.14

adele

-0.14

-sdk

-0.14

Joint

-0.14

POSITIVE LOGITS

racak

0.15

ych

0.14

 evasion

0.14

á»ĥn

0.14

YN

0.14

 conj

0.14

auen

0.14

 Unknown

0.14

ĺ

0.14

/assert

0.14

Activations Density 0.001%

elements related to programming or coding structures

No Comments

No Known Activations