INDEX

Explanations

references to timeframes and recurring events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 monthly

-0.18

 Monthly

-0.17

 tonight

-0.17

 weekly

-0.17

Monthly

-0.16

-0.15

rv

-0.15

 daily

-0.15

 Weekly

-0.15

 overnight

-0.15

POSITIVE LOGITS

 year

0.66

year

0.54

 years

0.53

å¹´

0.48

.year

0.47

 YEAR

0.46

 Year

0.45

 aÃ±o

0.44

_year

0.43

 Ã¥r

0.43

Activations Density 0.146%

references to timeframes and recurring events

No Comments

No Known Activations