INDEX

Explanations

phrases indicating election results or appointments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Falsy

-0.16

illac

-0.16

eldo

-0.16

PPER

-0.15

lash

-0.15

ury

-0.15

Mev

-0.15

celik

-0.15

aps

-0.14

reu

-0.14

POSITIVE LOGITS

0.16

kowski

0.16

åģ¥

0.16

 expans

0.15

ologi

0.14

fld

0.14

ATH

0.14

ÏĪÎ·

0.14

flo

0.14

ati

0.14

Activations Density 0.157%

phrases indicating election results or appointments

No Comments

No Known Activations