INDEX

Explanations

terms related to commercial classifications and transactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

immer

-0.14

 ÐľÐ¸

-0.14

mary

-0.13

 Classics

-0.13

 Manhattan

-0.13

entr

-0.13

gregated

-0.13

 Moor

-0.13

Dados

-0.13

 ëķ

-0.13

POSITIVE LOGITS

RFC

0.20

dpi

0.19

RFC

0.19

nit

0.19

 telefono

0.18

Nit

0.18

 email

0.18

nit

0.17

 Document

0.17

dpi

0.17

Activations Density 0.019%

terms related to commercial classifications and transactions

No Comments

No Known Activations