INDEX

Explanations

references to historical events and timelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

er

-0.17

id

-0.16

older

-0.15

 older

-0.15

lest

-0.15

hem

-0.14

le

-0.14

POSITIVE LOGITS

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.32

-era

0.31

era

0.29

decade

0.23

era

0.22

 period

0.20

Era

0.20

 dÃ¶nemde

0.20

 timeframe

0.20

hey

0.19

Activations Density 0.037%

references to historical events and timelines

No Comments

No Known Activations