INDEX

Explanations

character names and relationships 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

á»Ĳ

-0.17

cÃŃ

-0.17

iddet

-0.16

Î¼Î¿Î¯

-0.15

idders

-0.15

DataTask

-0.14

tplib

-0.14

ISCO

-0.14

enge

-0.14

-thumbnails

-0.14

POSITIVE LOGITS

essler

0.15

 Character

0.15

aya

0.14

“

0.14

Wid

0.14

=o

0.14

 Gilbert

0.14

icht

0.14

å¹³

0.14

’s

0.13

Activations Density 0.045%

character names and relationships in narratives

No Comments

No Known Activations