INDEX

Explanations

specific terms and names associated with movies and television shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Å¡t

-0.21

own

-0.18

/team

-0.15

ovenant

-0.15

ensively

-0.15

erd

-0.14

riad

-0.14

rial

-0.14

velt

-0.14

ick

-0.14

POSITIVE LOGITS

ushima

0.23

gether

0.20

asic

0.19

entieth

0.18

itionally

0.17

ÑĩÐ°Ñģ

0.17

esseract

0.17

UGHT

0.17

oretical

0.17

orrow

0.17

Activations Density 1.057%

specific terms and names associated with movies and television shows

No Comments

No Known Activations