INDEX

Explanations

custom specifications and configuration options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 hari

-0.15

é³´

-0.15

ast

-0.15

uja

-0.14

 Sunder

-0.14

ICODE

-0.14

 Consortium

-0.14

zend

-0.13

arin

-0.13

Ast

-0.13

POSITIVE LOGITS

refixer

0.16

Bond

0.15

axter

0.15

 Faction

0.15

pageNum

0.14

-Ta

0.14

 Bond

0.14

bond

0.14

ISON

0.14

’ÑĶ

0.14

Activations Density 0.238%

custom specifications and configuration options

No Comments

No Known Activations