INDEX

Explanations

pivotal events and claims in historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

rtc

-0.15

ogn

-0.15

ritz

-0.14

uzzi

-0.14

 rinse

-0.14

RPC

-0.14

vard

-0.14

reau

-0.14

leo

-0.13

íĥģ

-0.13

POSITIVE LOGITS

 Williams

1.37

Williams

1.25

 William

0.73

William

0.66

 Willi

0.56

 Williamson

0.54

 WILL

0.48

iams

0.46

 Willie

0.41

 Wilhelm

0.40

Activations Density 0.024%

pivotal events and claims in historical contexts

No Comments

No Known Activations