INDEX

Explanations

details about guest accommodations and amenities in a setting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

orners

-0.16

kke

-0.15

agne

-0.15

ÑĥÑĩÐ°

-0.14

 presence

-0.14

 loose

-0.14

Placement

-0.14

avras

-0.14

aper

-0.13

voir

-0.13

POSITIVE LOGITS

 WARRANT

0.14

ockey

0.14

 unin

0.14

dbl

0.14

Ø±Ø¯Ùĩ

0.13

ä»ĭ

0.13

ibal

0.13

 units

0.13

 shaving

0.13

destruct

0.13

Activations Density 0.052%

details about guest accommodations and amenities in a setting

No Comments

No Known Activations