INDEX

Explanations

references to geographical locations and their descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

una

-0.17

ouv

-0.14

yna

-0.14

onaut

-0.14

visor

-0.13

 Forbidden

-0.13

 Aberdeen

-0.13

oug

-0.13

ulg

-0.13

POSITIVE LOGITS

 Europe

0.33

Europe

0.25

 europe

0.24

 Ø§ÙĦØ¹Ø§ÙĦÙħ

0.20

 Europa

0.19

 England

0.19

 Asia

0.19

 France

0.17

urope

0.17

 globe

0.17

Activations Density 0.083%

references to geographical locations and their descriptions

No Comments

No Known Activations