INDEX

Explanations

references to features and amenities of a property

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Ð¸ÑĤÐ¾Ð¼

-0.16

Arm

-0.15

-0.14

 from

-0.14

 Down

-0.14

asal

-0.14

way

-0.13

 mitt

-0.13

POSITIVE LOGITS

ï»¿#

0.17

elease

0.16

toFloat

0.16

kker

0.15

phis

0.15

IPHER

0.15

angler

0.15

/Dk

0.15

ehr

0.14

_PD

0.14

Activations Density 0.068%

references to features and amenities of a property

No Comments

No Known Activations