INDEX

Explanations

elements related to action and thriller genres in movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 grand

-0.16

èĨ

-0.15

 grandchildren

-0.15

 robe

-0.14

div

-0.14

iences

-0.14

earer

-0.14

POSITIVE LOGITS

SND

0.15

 JetBrains

0.15

 tiener

0.15

 Feinstein

0.15

lec

0.14

KER

0.14

ANO

0.14

ardo

0.14

.offsetWidth

0.14

 NavParams

0.14

Activations Density 0.055%

elements related to action and thriller genres in movies

No Comments

No Known Activations