INDEX

Explanations

references to online services and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

inya

-0.15

 Stan

-0.15

urre

-0.15

 Johnston

-0.14

zar

-0.14

æ§

-0.14

-dismiss

-0.13

 Fate

-0.13

tent

-0.13

POSITIVE LOGITS

 Scotia

0.15

 gratuiti

0.14

 keycode

0.14

è²Į

0.14

 trial

0.14

bung

0.14

ellas

0.13

amac

0.13

Ð¸Ð½Ñĥ

0.13

>Error

0.13

Activations Density 0.042%

references to online services and their features

No Comments

No Known Activations