INDEX

Explanations

mentions of cinema and film-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

resse

-0.16

itan

-0.16

-0.15

ritt

-0.15

adiator

-0.15

oenix

-0.15

utsch

-0.15

resses

-0.15

ongan

-0.15

riÃ¨re

-0.14

POSITIVE LOGITS

ematic

0.30

emat

0.26

emas

0.26

ematics

0.22

ERGY

0.21

ergy

0.21

chy

0.20

EMA

0.20

emax

0.20

eworld

0.19

Activations Density 0.008%

mentions of cinema and film-related terms

No Comments

No Known Activations