INDEX

Explanations

elements related to governance and policy discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

piler

-0.15

upakan

-0.15

sz

-0.15

ollider

-0.15

Î¯Î¸

-0.14

cÃ©

-0.14

Î»ÎµÎº

-0.14

tick

-0.14

mÃ©

-0.14

ÐĲÑĢÑħÑĸÐ²

-0.14

POSITIVE LOGITS

.gr

0.24

ÎĦ

0.24

 Greek

0.24

 Athens

0.23

 Greece

0.23

 Cyprus

0.20

akis

0.20

 Dimit

0.20

Yi

0.19

Kou

0.19

Activations Density 0.113%

elements related to governance and policy discussions

No Comments

No Known Activations