INDEX

Explanations

references to historical artifacts and significant documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

hes

-0.17

å¢

-0.16

ahlen

-0.15

ÐµÐ½ÑĤÐ¸

-0.14

ë·

-0.14

RIEND

-0.13

ÑĢÑĥÐ½

-0.13

å»·

-0.13

ver

-0.13

POSITIVE LOGITS

ifact

0.17

 auction

0.17

-display

0.17

 housed

0.17

 museums

0.16

Å¡ak

0.16

 exhibited

0.16

 museum

0.16

 owned

0.15

 Museum

0.15

Activations Density 0.164%

references to historical artifacts and significant documents

No Comments

No Known Activations