INDEX

Explanations

references to alternative options or substitutions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

rlen

-0.16

à¹Īà¸²à¸ķ

-0.15

Vien

-0.15

 Wheeler

-0.14

naire

-0.14

bara

-0.14

Ð½Ð°Ð²

-0.14

geÃ§

-0.14

GP

-0.14

ToLeft

-0.14

POSITIVE LOGITS

issen

0.18

 Mane

0.16

olem

0.15

ios

0.15

 Commod

0.15

 bread

0.15

ilig

0.14

 peÅŁ

0.14

ledge

0.14

oman

0.14

Activations Density 0.003%

references to alternative options or substitutions in various contexts

No Comments

No Known Activations