INDEX

Explanations

references to the Supreme Court

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Ø¬ÙĪ

-0.16

Ø¹

-0.16

 ÑģÑĥÐ¼

-0.15

 Ð¾ÐºÐ¾Ð½

-0.15

aroo

-0.15

Ã¼b

-0.14

TEL

-0.14

aversal

-0.14

quiries

-0.14

laus

-0.14

POSITIVE LOGITS

 Court

0.23

Court

0.20

uros

0.18

 court

0.16

ouch

0.15

 COURT

0.15

ali

0.15

et

0.15

ure

0.15

Activations Density 0.010%

references to the Supreme Court

No Comments

No Known Activations