INDEX

Explanations

references to dyeing and mordanting processes

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

_checkpoint

-0.15

cente

-0.14

à¸°

-0.14

ÙĪÙĩ

-0.14

 cáº§u

-0.13

 joystick

-0.13

erdale

-0.13

ÙĪÙħÛĮ

-0.13

Checkpoint

-0.13

InView

-0.12

POSITIVE LOGITS

dye

0.35

dy

0.35

Dy

0.27

vat

0.27

 bath

0.25

 dying

0.24

dy

0.24

 baths

0.24

æŁĵ

0.23

 colour

0.22

Activations Density 0.032%

references to dyeing and mordanting processes

No Comments

No Known Activations