INDEX

Explanations

phrases related to housing and accommodations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

orque

-0.15

kop

-0.15

 Belle

-0.14

 more

-0.14

 molded

-0.13

 strain

-0.13

 suspected

-0.13

 Ð¢ÑĥÑĤ

-0.13

 drawn

-0.13

Builders

-0.13

POSITIVE LOGITS

 Engineer

0.14

itespace

0.14

oven

0.14

 Mouth

0.14

aldo

0.14

 bills

0.14

enne

0.14

ANNER

0.14

usi

0.14

 scÃ©

0.14

Activations Density 0.487%

phrases related to housing and accommodations

No Comments

No Known Activations