INDEX

Explanations

terms related to power and energy sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ibaba

-0.15

eways

-0.15

afari

-0.15

eker

-0.15

iban

-0.15

inois

-0.14

bable

-0.14

ê¸ī

-0.14

Å¡tÄĽnÃŃ

-0.14

eward

-0.14

POSITIVE LOGITS

fully

0.26

0.19

full

0.18

ful

0.17

iture

0.17

/power

0.17

chest

0.17

lier

0.15

vang

0.15

edList

0.15

Activations Density 0.046%

terms related to power and energy sources

No Comments

No Known Activations