INDEX

Explanations

words associated with drama and intensity 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 latter

-0.20

ie

-0.17

bie

-0.16

bil

-0.15

ieg

-0.15

ies

-0.15

auer

-0.15

oo

-0.15

bag

-0.15

edom

-0.14

POSITIVE LOGITS

íĭ±

0.20

atically

0.19

atic

0.18

-document

0.18

 queen

0.18

/com

0.16

 queens

0.16

 llama

0.16

usp

0.15

Activations Density 0.023%

words associated with drama and intensity in narratives

No Comments

No Known Activations