INDEX

Explanations

numerical figures associated with 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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 Kramer

-0.16

-0.15

å²³

-0.15

é³

-0.15

åĩ

-0.15

 hÃ¡t

-0.14

ÐµÐºÐ¾

-0.14

anson

-0.14

abeth

-0.14

ens

-0.14

POSITIVE LOGITS

isz

0.16

isman

0.15

ittest

0.14

ambi

0.14

_VIRTUAL

0.14

ffa

0.13

èĭ

0.13

 Meal

0.13

 Manual

0.13

FINE

0.13

Activations Density 0.013%

numerical figures associated with distances or measurements

No Comments

No Known Activations