INDEX

Explanations

elements related to plot structure and points in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

oe

-0.16

hood

-0.15

JI

-0.15

á»ħ

-0.15

hart

-0.15

het

-0.15

prises

-0.15

POSITIVE LOGITS

ting

0.39

ter

0.38

tery

0.26

TER

0.22

line

0.22

TERS

0.20

te

0.20

tere

0.19

iful

0.19

ural

0.19

Activations Density 0.010%

elements related to plot structure and points in narratives

No Comments

No Known Activations