INDEX

Explanations

numerical relationships and patterns related to time and personal attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Sanity

-0.15

olk

-0.14

 ÑĩÑĥÐ²

-0.14

çĴĥ

-0.14

 erst

-0.14

åłĤ

-0.14

 amongst

-0.14

callable

-0.14

akan

-0.13

 Elegant

-0.13

POSITIVE LOGITS

âĦĸ

0.19

descr

0.18

Ðµ

0.18

 standart

0.17

Ñģ

0.17

 Ñģ

0.17

 Ð¾

0.16

 Ð¡

0.15

 singled

0.15

 Ðľ

0.15

Activations Density 0.125%

numerical relationships and patterns related to time and personal attributes

No Comments

No Known Activations