INDEX

Explanations

phrases indicating specific moments or points in time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

edes

-0.18

ock

-0.15

isateur

-0.14

@mail

-0.14

ikan

-0.14

à¸Ńà¸ĩ

-0.13

egt

-0.13

Ø¡

-0.13

 hemen

-0.13

ocker

-0.13

POSITIVE LOGITS

at

0.43

At

0.25

 times

0.25

 moment

0.23

At

0.22

_at

0.22

 táº¡i

0.21

 once

0.20

 momento

0.20

æĻĤ

0.20

Activations Density 0.123%

phrases indicating specific moments or points in time

No Comments

No Known Activations