INDEX

Explanations

specific dates and references to events or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

(íģ¬ê¸°

-0.17

..↵↵↵↵

-0.17

 ìĥĪê¸Ģ

-0.16

 ëĦ¤ìĿ´íĬ¸

-0.15

 íĮĮìĿ¼ì²¨ë¶Ģ

-0.15

 ãħĩãħĩ

-0.14

 ë¨

-0.14

 åıĮçº¿

-0.13

 ë¸

-0.13

 ëĭ¤ìļ´ë°Ľê¸°

-0.13

POSITIVE LOGITS

0.82

0.76

0.69

0.66

0.61

0.55

0.51

0.46

0.41

0.40

Activations Density 1.152%

specific dates and references to events or activities

No Comments

No Known Activations