INDEX

Explanations

legal terminology and references to regulations or statutes

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

inth

-0.15

anghai

-0.15

issing

-0.15

amazon

-0.15

ottes

-0.14

inder

-0.14

untu

-0.14

orsk

-0.14

Wid

-0.14

ieux

-0.14

POSITIVE LOGITS

 TextAlign

0.17

hte

0.15

keit

0.15

utin

0.14

.Bunifu

0.14

ÑĥÑĩÐ°

0.14

ãĥ©ãĤ¯

0.14

 MetroFramework

0.14

à¹ĩà¸ĩ

0.14

oki

0.13

Activations Density 0.023%

legal terminology and references to regulations or statutes

No Comments

No Known Activations