INDEX

Explanations

references to specific individuals involved in events or legal situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ÑĢÑĥÑĩ

-0.15

oit

-0.15

marks

-0.15

mary

-0.15

 Punch

-0.14

Ã¨m

-0.14

ester

-0.14

ive

-0.14

ellular

-0.14

POSITIVE LOGITS

 ours

0.17

 theirs

0.15

éĴ®

0.15

Geh

0.15

Ø´Ø¯

0.14

 Coupe

0.14

aida

0.14

 Barney

0.14

afe

0.14

 personals

0.13

Activations Density 0.401%

references to specific individuals involved in events or legal situations

No Comments

No Known Activations