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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.15

unma

-0.15

ÑĩÐ°ÑĤ

-0.15

jee

-0.15

 Rafael

-0.14

tings

-0.14

à¥Ģà¤ª

-0.13

 empire

-0.13

iswa

-0.13

ÑĩÐ°

-0.13

POSITIVE LOGITS

uros

0.18

 Court

0.15

iy

0.15

aso

0.15

âĨĳ

0.15

 enim

0.14

æĿī

0.14

heit

0.14

SSION

0.14

 âĨĳ

0.14

Activations Density 0.018%

references to the Supreme Court

No Comments

No Known Activations