INDEX

Explanations

descriptive adjectives and the use of vivid imagery in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

mina

-0.16

ÐµÐ²Ð¾Ð¹

-0.15

arde

-0.14

 Decomp

-0.14

-www

-0.14

arshal

-0.14

æĨ

-0.14

ÂłPS

-0.13

asca

-0.13

 setFrame

-0.13

POSITIVE LOGITS

uten

0.17

Ã³ng

0.14

.untracked

0.14

yet

0.14

iji

0.14

Å¡ak

0.13

åľĺ

0.13

utow

0.13

ãģ¾ãģ§

0.13

loit

0.13

Activations Density 0.374%

descriptive adjectives and the use of vivid imagery in narratives

No Comments

No Known Activations