INDEX

Explanations

aspects related to narrative complexity and emotional states in storytelling

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

 notably

-0.23

 notion

-0.21

ext

-0.21

 nervous

-0.20

à¤Ĺà¤°

-0.20

 notions

-0.20

 necessary

-0.20

 notable

-0.20

iar

-0.19

 noticeable

-0.19

POSITIVE LOGITS

veau

0.21

 táº£ng

0.21

theless

0.19

withstanding

0.19

olson

0.18

tie

0.18

lify

0.17

=N

0.17

stand

0.17

istic

0.17

Activations Density 1.215%

aspects related to narrative complexity and emotional states in storytelling

No Comments

No Known Activations