INDEX

Explanations

references to cinema and film-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ilk

-0.17

.scalablytyped

-0.15

off

-0.14

stable

-0.14

 invasive

-0.14

wind

-0.14

alm

-0.14

ìŁģ

-0.14

 Clement

-0.13

POSITIVE LOGITS

ematic

0.20

ERGY

0.19

ical

0.18

ergy

0.17

ematics

0.17

emas

0.16

emat

0.16

è£ı

0.16

rh

0.15

esthetic

0.15

Activations Density 0.014%

references to cinema and film-related terminology

No Comments

No Known Activations