INDEX

Explanations

titles and their formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

unsch

-0.16

"class

-0.15

ients

-0.14

pus

-0.14

ialect

-0.14

qid

-0.14

lication

-0.14

 QuÃ½

-0.14

estruction

-0.14

struction

-0.14

POSITIVE LOGITS

posit

0.17

/title

0.16

celik

0.16

 insurance

0.15

thal

0.15

owitz

0.15

alers

0.15

 Loans

0.15

Ð¾Ð²Ñĸ

0.14

 title

0.14

Activations Density 0.006%

titles and their formatting

No Comments

No Known Activations