INDEX

Explanations

quantities of people or groups referenced in a context that suggests common experiences or trends

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

Dyn

-0.16

fusc

-0.15

ancias

-0.15

ELS

-0.15

enschaft

-0.15

grounds

-0.15

ialis

-0.14

uve

-0.14

Î»Î¹Îº

-0.14

imus

-0.14

POSITIVE LOGITS

Ups

0.17

vinc

0.16

 McConnell

0.15

pit

0.15

ElementsBy

0.14

ValueType

0.14

cum

0.14

Vz

0.14

Subtitle

0.14

 Howe

0.14

Activations Density 0.005%

quantities of people or groups referenced in a context that suggests common experiences or trends

No Comments

No Known Activations