INDEX

Explanations

expressions of surprise or shock

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

rex

-0.14

xsd

-0.13

&&!

-0.13

 Ð¿Ð¾Ð´Ð²

-0.13

_IOC

-0.13

 Radius

-0.13

 press

-0.13

ropy

-0.13

.tap

-0.13

ÑıÐ´

-0.13

POSITIVE LOGITS

ordova

0.17

Ð¼Ð¸ÑĢ

0.16

 Kidd

0.15

Teh

0.15

ingly

0.15

WTF

0.15

naz

0.14

 Sala

0.14

prises

0.14

 surprise

0.14

Activations Density 0.237%

expressions of surprise or shock

No Comments

No Known Activations