INDEX

Explanations

references to the Associated Press (AP) news agency and reporting style

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

abo

-0.15

pell

-0.15

Ø§ØµÙĦ

-0.14

sharing

-0.14

lettes

-0.14

abus

-0.14

.BO

-0.14

ToObject

-0.14

CompanyName

-0.14

aversal

-0.14

POSITIVE LOGITS

 nationalists

0.15

iem

0.15

 Associated

0.15

 nationalist

0.14

AP

0.14

 titanium

0.14

çĢ

0.14

anga

0.14

ãģĵãģ¨ãģ«

0.14

Activations Density 0.009%

references to the Associated Press (AP) news agency and reporting style

No Comments

No Known Activations