INDEX

Explanations

content related to literary achievements and author backgrounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

neys

-0.16

imoto

-0.15

å¥ı

-0.14

 Architect

-0.14

uml

-0.14

 Fiscal

-0.13

ovah

-0.13

 Techn

-0.13

 Vide

-0.13

 Pitch

-0.13

POSITIVE LOGITS

 literature

0.49

 Literature

0.49

 novels

0.40

Liter

0.40

liter

0.40

 literary

0.40

 fiction

0.40

 liter

0.37

 novel

0.36

-liter

0.36

Activations Density 0.281%

content related to literary achievements and author backgrounds

No Comments

No Known Activations