INDEX

Explanations

references to online resources and hyperlinks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

addy

-0.14

ezier

-0.14

otec

-0.14

Arb

-0.14

areth

-0.13

 Clips

-0.13

Ã¡Å¾

-0.13

 Ging

-0.13

.theme

-0.13

ms

-0.13

POSITIVE LOGITS

nown

0.18

 Cock

0.16

irler

0.15

PKG

0.14

nova

0.14

bek

0.14

sono

0.14

ossible

0.14

Smarty

0.14

Activations Density 0.364%

references to online resources and hyperlinks

No Comments

No Known Activations