INDEX

Explanations

key performance indicators and rankings related to 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 @ 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

utow

-0.14

kami

-0.14

 Pike

-0.14

MAP

-0.14

thes

-0.14

keh

-0.14

ARK

-0.13

 Rencontre

-0.13

esda

-0.13

 Ware

-0.13

POSITIVE LOGITS

ruc

0.16

phere

0.16

.sponge

0.14

 meteor

0.13

ircle

0.13

zen

0.13

 Sellers

0.13

èĺĩ

0.13

ospace

0.13

osphere

0.13

Activations Density 0.057%

key performance indicators and rankings related to various contexts

No Comments

No Known Activations