INDEX

Explanations

references to video content, particularly movies and visual 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

UGIN

-0.15

coli

-0.14

utable

-0.14

PFN

-0.14

atedRoute

-0.14

 (!((

-0.14

AffineTransform

-0.14

STALL

-0.14

á»¥c

-0.13

mere

-0.13

POSITIVE LOGITS

oodoo

0.29

amp

0.29

ampire

0.28

HS

0.27

amps

0.26

ibe

0.26

odka

0.24

agina

0.24

omit

0.24

ulture

0.24

Activations Density 0.027%

references to video content, particularly movies and visual media

No Comments

No Known Activations