INDEX

Explanations

references to geopolitical issues and actions related to Russia

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

-0.15

ISA

-0.15

SSR

-0.14

é»İ

-0.14

 Swal

-0.14

allo

-0.14

 Cyan

-0.14

anyl

-0.14

aal

-0.14

POSITIVE LOGITS

 Federation

0.22

 Komm

0.20

 Wagner

0.19

 Rossi

0.19

Gaz

0.18

Nez

0.18

.Put

0.18

PUT

0.17

kre

0.17

 Kremlin

0.17

Activations Density 0.055%

references to geopolitical issues and actions related to Russia

No Comments

No Known Activations