INDEX

Explanations

references to missing or lost individuals and their circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

eled

-0.16

ydk

-0.15

 hereby

-0.15

ÑĢÑĥÐ±

-0.14

wick

-0.14

aal

-0.13

ownik

-0.13

avn

-0.13

uni

-0.13

berman

-0.13

POSITIVE LOGITS

 earlier

0.26

 previously

0.24

 Earlier

0.19

Previously

0.18

 previous

0.17

 ÑĢÐ°Ð½ÑĮÑĪÐµ

0.17

Earlier

0.17

 Previously

0.17

 recently

0.15

previous

0.15

Activations Density 0.387%

references to missing or lost individuals and their circumstances

No Comments

No Known Activations