INDEX

Explanations

specific names or proper nouns related to individuals in professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

WTF

-0.18

 dude

-0.18

 freaking

-0.17

 FUCK

-0.16

('

-0.15

 (“

-0.15

OK

-0.15

ok

-0.15

 badass

-0.15

POSITIVE LOGITS

 folk

0.18

folk

0.17

 gossip

0.17

 clustering

0.17

 clustered

0.15

 talk

0.15

wag

0.15

 Clan

0.15

 clans

0.15

--↵

0.14

Activations Density 0.003%

specific names or proper nouns related to individuals in professional contexts

No Comments

No Known Activations