INDEX

Explanations

temporal indicators and event references

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

 Third

-0.20

 Fourth

-0.20

Third

-0.18

Fourth

-0.17

 fourth

-0.17

à¸±à¸Ļà¸¢à¸²à¸¢à¸Ļ

-0.17

 THIRD

-0.17

_third

-0.17

 third

-0.15

 ç¬¬ä¸ī

-0.15

POSITIVE LOGITS

 February

0.70

Feb

0.67

February

0.65

Feb

0.63

-Feb

0.54

0.52

 Åŀubat

0.47

 ÑĦÐµÐ²ÑĢÐ°Ð»Ñı

0.47

 ÑĦÐµÐ²

0.46

fe

0.45

Activations Density 0.152%

temporal indicators and event references

No Comments

No Known Activations