INDEX

Explanations

terms related to specific legal or medical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Ð¿ÑĥÑģÑĤ

-0.15

icamente

-0.14

bsite

-0.14

browse

-0.14

ACHINE

-0.14

shint

-0.14

ç¢

-0.14

ulus

-0.14

elter

-0.13

ethe

-0.13

POSITIVE LOGITS

Ð²Ð¸ÑĤ

0.16

 ballo

0.15

abo

0.15

ubat

0.15

ungs

0.15

0.14

ckt

0.14

 Loft

0.14

pie

0.14

arg

0.14

Activations Density 0.021%

terms related to specific legal or medical concepts

No Comments

No Known Activations