INDEX

Explanations

phrases indicating presence, offerings, and features of services or amenities

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

-lfs

-0.14

Rue

-0.14

Unmarshaller

-0.14

osexual

-0.14

pons

-0.14

Ð½ÑĸÐ²

-0.14

ÑģÑĤÑĢÑĥ

-0.14

ConverterFactory

-0.14

ë³µ

-0.14

WithIdentifier

-0.14

POSITIVE LOGITS

 Prote

0.14

gov

0.14

Sud

0.14

 damage

0.14

th

0.13

uf

0.13

 parts

0.13

 CGRectGet

0.13

erra

0.13

Activations Density 0.766%

phrases indicating presence, offerings, and features of services or amenities

No Comments

No Known Activations