INDEX

Explanations

instances of notable events and highlights in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

leasing

-0.16

decorators

-0.15

BIT

-0.15

omu

-0.15

ignet

-0.15

BIT

-0.15

REA

-0.15

Ã´m

-0.14

sono

-0.14

 bitten

-0.14

POSITIVE LOGITS

by

0.27

 ØªÙĪØ³Ø·

0.27

 oleh

0.25

 bá»Łi

0.24

 Ø¨ÙĪØ§Ø³Ø·Ø©

0.21

çĶ±

0.17

anship

0.16

 çĶ±

0.16

 ìĿĺíķ´

0.16

by

0.15

Activations Density 0.712%

instances of notable events and highlights in various contexts

No Comments

No Known Activations

instances of notable events and highlights in various contexts

No Comments

No Known Activations