INDEX

Explanations

recurring themes and tropes in storytelling, particularly in film and literature

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

rada

-0.16

gem

-0.14

(defvar

-0.14

enek

-0.14

rama

-0.14

cac

-0.14

zem

-0.13

æ··

-0.13

urd

-0.13

uptime

-0.13

POSITIVE LOGITS

 familiar

0.34

 trop

0.31

 formula

0.31

 trope

0.28

 clich

0.28

 template

0.28

formula

0.25

 classic

0.25

 formulas

0.24

 typical

0.23

Activations Density 0.194%

recurring themes and tropes in storytelling, particularly in film and literature

No Comments

No Known Activations