INDEX

Explanations

references to film production and filmmaking details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ghost

-0.15

igt

-0.15

ej

-0.15

oner

-0.14

 knots

-0.14

Bij

-0.14

 cuffs

-0.14

NA

-0.14

 ghosts

-0.14

 ghost

-0.13

POSITIVE LOGITS

orno

0.17

esture

0.14

uttle

0.14

ctp

0.14

sek

0.14

utan

0.14

oron

0.14

etc

0.14

uards

0.13

 Nolan

0.13

Activations Density 0.273%

references to film production and filmmaking details

No Comments

No Known Activations