INDEX

Explanations

sections of text containing organizational categories or labels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

iminal

-0.18

-0.16

ge

-0.14

à¸µà¸ģ

-0.14

anken

-0.14

aju

-0.13

ä¸įè¶³

-0.13

 Raphael

-0.13

itzer

-0.13

,user

-0.13

POSITIVE LOGITS

Ð½Ð¾Ð¿

0.15

ulas

0.15

eya

0.14

feb

0.14

æľĽ

0.14

à¹Ģà¸«à¸Ļ

0.14

FromNib

0.14

ToSelector

0.14

irsch

0.14

ogui

0.14

Activations Density 0.034%

sections of text containing organizational categories or labels

No Comments

No Known Activations