INDEX

Explanations

references to dramatic themes and storytelling elements

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

iad

-0.17

Ð·Ð¸

-0.15

_female

-0.15

zik

-0.14

 trusts

-0.14

aris

-0.14

ae

-0.14

Ð´ÐµÐ¼

-0.14

.foundation

-0.13

omik

-0.13

POSITIVE LOGITS

-addons

0.16

Ã´t

0.16

 Flynn

0.14

 INCIDENTAL

0.14

oy

0.14

 ÙħØ¨Ø§Ø´

0.14

¢åįķ

0.14

å·±

0.13

.getMap

0.13

åħ·

0.13

Activations Density 0.004%

references to dramatic themes and storytelling elements

No Comments

No Known Activations