INDEX

Explanations

discussions comparing narrative focus or thematic changes 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

my

-0.16

 indeed

-0.14

 simply

-0.14

may

-0.14

 should

-0.14

ë¿Ĳ

-0.13

 cannot

-0.13

 truly

-0.13

ama

-0.13

 simple

-0.13

POSITIVE LOGITS

 yourselves

0.32

 yourself

0.31

 youre

0.24

ä½łçļĦ

0.23

your

0.23

 your

0.22

 Yourself

0.21

)?↵

0.20

ä½ł

0.19

ï¼Ł↵

0.19

Activations Density 0.279%

discussions comparing narrative focus or thematic changes in storytelling

No Comments

No Known Activations