INDEX

Explanations

mentions of various foundations and their associated topics or missions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Epic

-0.15

Mike

-0.14

auer

-0.14

,nil

-0.13

áº¡p

-0.13

usra

-0.13

.VideoCapture

-0.13

 culpa

-0.13

POSITIVE LOGITS

 forgotten

0.15

Ð¾ÐºÐ¾Ð½

0.15

Ð¶Ð´

0.14

iqueta

0.14

adia

0.14

Adv

0.14

hei

0.14

 conserv

0.13

 verd

0.13

_eye

0.13

Activations Density 0.014%

mentions of various foundations and their associated topics or missions

No Comments

No Known Activations