INDEX

Explanations

numerical representations of distances or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ubat

-0.16

urve

-0.15

.wp

-0.14

urette

-0.14

iry

-0.14

wp

-0.14

odata

-0.14

_MP

-0.14

 Cells

-0.14

Å¾i

-0.13

POSITIVE LOGITS

 away

0.33

 miles

0.32

km

0.31

mi

0.29

away

0.27

 Away

0.26

Âłmi

0.24

 Miles

0.24

-away

0.22

Away

0.22

Activations Density 0.003%

numerical representations of distances or measurements

No Comments

No Known Activations