INDEX

Explanations

instances of numerical or statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oling

-0.16

mares

-0.15

uais

-0.14

awan

-0.14

¼

-0.14

ÑģÑĭÐ»

-0.13

orpion

-0.13

andre

-0.13

 Hlav

-0.13

eprom

-0.13

POSITIVE LOGITS

 NotificationCenter

0.15

istrat

0.14

PRESS

0.14

ãĥ¼ãĤº

0.14

ichick

0.14

ãĤ¤ãĥ¤

0.14

0.13

âĹİ

0.13

zych

0.13

Activations Density 0.003%

instances of numerical or statistical information

No Comments

No Known Activations