INDEX

Explanations

proper nouns, particularly names of people related to movies or media

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

-0.27

 macOS

-0.25

 ðŁĶ

-0.24

https

-0.24

ðĿ

-0.24

ðŁĴ

-0.23

 ðŁĳ

-0.23

 https

-0.23

ðŁ

-0.23

ðŁĺ

-0.23

POSITIVE LOGITS

TMZ

0.30

 Lindsay

0.26

VH

0.25

 cele

0.25

pap

0.23

 Celebrity

0.23

MTV

0.23

 Paris

0.22

 Perez

0.22

 Radar

0.21

Activations Density 0.063%

proper nouns, particularly names of people related to movies or media

No Comments

No Known Activations