INDEX

Explanations

words related to governance and political entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

er

-0.23

eron

-0.18

erne

-0.17

Ã³l

-0.17

erro

-0.17

erer

-0.16

erap

-0.16

å¹ķ

-0.16

erp

-0.15

erot

-0.15

POSITIVE LOGITS

itch

0.20

adia

0.19

antage

0.19

ascular

0.18

à¥įà¤¹

0.17

aled

0.17

ariate

0.16

olution

0.16

ell

0.16

anni

0.16

Activations Density 0.026%

words related to governance and political entities

No Comments

No Known Activations