INDEX

Explanations

character names and relational dynamics in stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 also

-0.14

blink

-0.14

 anche

-0.14

 mote

-0.14

edback

-0.14

Also

-0.14

 subsequent

-0.14

ãģ«ãĤĤ

-0.13

itol

-0.13

ynet

-0.13

POSITIVE LOGITS

 wake

0.23

 decide

0.22

 Wake

0.22

 wakes

0.21

woke

0.21

 suddenly

0.21

 woke

0.20

 decides

0.20

 decided

0.20

 innoc

0.19

Activations Density 0.291%

character names and relational dynamics in stories

No Comments

No Known Activations