INDEX

Explanations

references to significant historical events and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ani

-0.15

ovsky

-0.14

è®¸

-0.14

atsu

-0.14

ÙĦÙĪ

-0.14

.ts

-0.13

Ud

-0.13

qtt

-0.13

ä½¿

-0.13

à¸±à¸įà¸į

-0.13

POSITIVE LOGITS

 yerine

0.20

 replaced

0.19

ugen

0.16

 à¹Ĩ

0.16

kker

0.15

 bá»ı

0.15

aked

0.15

anza

0.15

ytt

0.15

lest

0.14

Activations Density 0.227%

references to significant historical events and their implications

No Comments

No Known Activations