INDEX

Explanations

technical terms related to parameters in various contexts

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

erman

-0.20

ress

-0.18

arga

-0.17

resses

-0.17

atel

-0.17

eyi

-0.17

resse

-0.16

ear

-0.16

eltas

-0.16

elier

-0.16

POSITIVE LOGITS

ized

0.28

etrize

0.26

ater

0.24

etric

0.24

ization

0.23

ised

0.23

etr

0.23

ter

0.22

aters

0.21

izable

0.21

Activations Density 0.035%

technical terms related to parameters in various contexts

No Comments

No Known Activations