INDEX

Explanations

numerical data or coding elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

-0.16

-0.15

vide

-0.15

antan

-0.15

-0.14

Fol

-0.13

rian

-0.13

à¸±à¸įà¸Ĭ

-0.13

gado

-0.13

POSITIVE LOGITS

VERR

0.17

 Giang

0.16

lek

0.15

RAIN

0.15

avery

0.14

elo

0.14

elm

0.14

edd

0.14

_UNITS

0.14

osta

0.14

Activations Density 0.023%

numerical data or coding elements

No Comments

No Known Activations