INDEX

Explanations

elements related to suspense and unanswered questions 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 @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 spect

-0.18

 Engineering

-0.18

 engineering

-0.15

 Unsigned

-0.15

Engineering

-0.15

 Engineer

-0.15

 venue

-0.15

 Imperial

-0.14

 pirate

-0.14

 engineers

-0.14

POSITIVE LOGITS

 Lynch

0.20

kowski

0.17

TeV

0.15

altung

0.15

.Areas

0.15

 cult

0.15

aleb

0.15

lington

0.15

à¤ªà¤¨

0.14

ģm

0.14

Activations Density 0.099%

elements related to suspense and unanswered questions in narratives

No Comments

No Known Activations