INDEX

Explanations

terms related to processes and actions in various contexts, specifically focusing on verbs and their implications

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

 Ramp

-0.19

ÑĥÑĢÐ³

-0.15

ÑįÑĦ

-0.15

oker

-0.15

omanip

-0.14

elivery

-0.14

-max

-0.14

Configurer

-0.14

touch

-0.14

ledon

-0.14

POSITIVE LOGITS

iant

0.17

 card

0.15

los

0.15

arna

0.15

tring

0.15

iar

0.14

 Hack

0.14

pls

0.14

ult

0.13

ULT

0.13

Activations Density 0.204%

terms related to processes and actions in various contexts, specifically focusing on verbs and their implications

No Comments

No Known Activations