INDEX

Explanations

references to geek culture and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Hlav

-0.16

olet

-0.15

å¥ī

-0.15

mpl

-0.15

FromArray

-0.14

eel

-0.14

ROUT

-0.14

ãĥĥãĥģ

-0.14

imeo

-0.14

 Creed

-0.14

POSITIVE LOGITS

ner

0.22

dy

0.22

ds

0.21

vana

0.19

Ner

0.18

uda

0.17

anyahu

0.16

anel

0.16

cess

0.16

edeyse

0.15

Activations Density 0.009%

references to geek culture and related terminology

No Comments

No Known Activations