INDEX

Explanations

expressions indicating an increase or enhancement

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

hani

-0.18

asers

-0.17

Nug

-0.16

ãģĻãģİ

-0.16

AINED

-0.16

acha

-0.15

asia

-0.14

RectTransform

-0.14

amage

-0.14

 localVar

-0.14

POSITIVE LOGITS

 than

0.18

 reverse

0.17

Than

0.16

irth

0.16

eger

0.15

MORE

0.14

 underlying

0.14

 Works

0.14

 worse

0.14

more

0.14

Activations Density 0.054%

expressions indicating an increase or enhancement

No Comments

No Known Activations