INDEX

Explanations

components and relationships in elements of a system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

reds

-0.14

 ÑĩÐµÑĢÐ²

-0.14

 tangled

-0.14

 ìĺģ

-0.14

ickerView

-0.14

ioc

-0.14

Leap

-0.14

Tank

-0.14

anik

-0.13

ules

-0.13

POSITIVE LOGITS

innacle

0.22

uss

0.17

 econ

0.15

Genres

0.15

awai

0.15

adam

0.14

 undert

0.14

idth

0.14

Mig

0.14

-minus

0.14

Activations Density 0.011%

components and relationships in elements of a system

No Comments

No Known Activations