INDEX

Explanations

references to specific organizations and their social media presence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

à¯į

-0.16

ingly

-0.15

 Ashe

-0.15

indre

-0.15

evi

-0.14

Zum

-0.14

Î½Î¿Ïį

-0.14

iyel

-0.14

ãĥ³ãĤ°

-0.14

å°ĺ

-0.14

POSITIVE LOGITS

ia

0.24

0.23

ka

0.22

ita

0.22

ja

0.21

ta

0.21

ua

0.20

sa

0.20

ma

0.20

ela

0.19

Activations Density 0.292%

references to specific organizations and their social media presence

No Comments

No Known Activations