INDEX

Explanations

elements associated with storytelling and narrative structure

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

ØºØ§ÙĦ

-0.16

 Å¾iv

-0.14

anness

-0.14

Ð²Ð¾Ðº

-0.14

osomal

-0.14

rita

-0.13

stderr

-0.13

è¼Ŀ

-0.13

utz

-0.13

atown

-0.13

POSITIVE LOGITS

die

0.36

 discrim

0.28

 fans

0.28

 discern

0.28

 lovers

0.27

 devoted

0.25

 lover

0.25

die

0.25

 devote

0.24

Die

0.24

Activations Density 0.340%

elements associated with storytelling and narrative structure

No Comments

No Known Activations