INDEX

Explanations

terms related to architecture and architectural design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

tings

-0.15

icity

-0.15

ÑĥÑĪÐºÐ¸

-0.15

yun

-0.15

ceptive

-0.14

arious

-0.14

optera

-0.14

oby

-0.14

oo

-0.14

POSITIVE LOGITS

urally

0.35

ural

0.33

URAL

0.26

/engine

0.25

itect

0.22

 sÆ°

0.22

onical

0.21

ivist

0.20

å¸Ī

0.19

ipel

0.19

Activations Density 0.015%

terms related to architecture and architectural design

No Comments

No Known Activations