INDEX

Explanations

terms related to image processing and color formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ridor

-0.17

acente

-0.15

MMC

-0.15

inely

-0.14

ê·¹

-0.14

angelog

-0.14

atcher

-0.14

ilde

-0.14

 Randall

-0.14

POSITIVE LOGITS

0.26

 prem

0.25

 channels

0.24

 channel

0.23

 Prem

0.22

 Channels

0.22

 Channel

0.21

.channels

0.20

RG

0.20

Activations Density 0.047%

terms related to image processing and color formats

No Comments

No Known Activations