INDEX

Explanations

references to movies and TV shows within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Annunci

-0.17

Dod

-0.15

 Disqus

-0.15

.blob

-0.14

ategorized

-0.14

edio

-0.14

á»įng

-0.14

Ã¤ng

-0.13

Cancelled

-0.13

subpackage

-0.13

POSITIVE LOGITS

 movie

0.15

movie

0.15

 artificial

0.14

heimer

0.13

bib

0.13

 movies

0.13

 è·

0.13

leo

0.13

dep

0.13

nil

0.13

Activations Density 0.360%

references to movies and TV shows within a context

No Comments

No Known Activations