INDEX

Explanations

phrases related to rankings and popularity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

idar

-0.15

jal

-0.15

ÏĥÏĩ

-0.14

/interface

-0.13

olian

-0.13

nung

-0.13

zon

-0.13

excerpt

-0.13

embre

-0.13

POSITIVE LOGITS

iske

0.18

ech

0.15

_ten

0.15

Disk

0.14

ten

0.14

Accessory

0.14

sville

0.14

disk

0.14

icode

0.14

ech

0.14

Activations Density 0.014%

phrases related to rankings and popularity

No Comments

No Known Activations