INDEX

Explanations

references to images or photos in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

olina

-0.16

Ð½Ð¾Ñĩ

-0.16

erness

-0.16

 Alexis

-0.15

 Viewer

-0.14

 greed

-0.14

 Kaynak

-0.14

ussion

-0.14

essler

-0.14

-produ

-0.14

POSITIVE LOGITS

.widgets

0.18

tuk

0.16

ħ§

0.15

ori

0.14

Ras

0.14

 Dock

0.14

.Contract

0.14

ftime

0.14

0.13

Activations Density 0.033%

references to images or photos in the text

No Comments

No Known Activations