INDEX

Explanations

references to height measurements, particularly in feet and inches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

beck

-0.18

adle

-0.15

itan

-0.15

ako

-0.15

ÏĢÎµ

-0.15

akest

-0.15

ient

-0.14

kommen

-0.14

Fonts

-0.14

-bodied

-0.14

POSITIVE LOGITS

 foot

0.31

foot

0.26

-foot

0.26

 feet

0.25

 tall

0.24

0.23

Height

0.22

 footer

0.22

 Foot

0.21

 HEIGHT

0.21

Activations Density 0.015%

references to height measurements, particularly in feet and inches

No Comments

No Known Activations