INDEX

Explanations

phrases or contexts indicating an entry or involvement in something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Theft

-0.15

æľĽ

-0.14

ientos

-0.13

kol

-0.13

Holder

-0.13

rej

-0.13

Imm

-0.13

hoff

-0.13

stoff

-0.13

æ²¹

-0.13

POSITIVE LOGITS

emple

0.15

 Lomb

0.15

aller

0.14

ARRANT

0.14

incare

0.14

ÑĪÐºÐ¸

0.14

olley

0.14

ãĤ«ãĥ¼

0.14

 Gram

0.13

oho

0.13

Activations Density 0.018%

phrases or contexts indicating an entry or involvement in something

No Comments

No Known Activations