INDEX

Explanations

references to articles and their metadata

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 presence

-0.15

 presidential

-0.14

ude

-0.14

MAS

-0.14

ancement

-0.14

mas

-0.14

antha

-0.14

Ð·ÑĮ

-0.14

 organization

-0.14

or

-0.14

POSITIVE LOGITS

_critical

0.14

 Vander

0.14

ecera

0.14

à¸±à¸ŀà¸Ĺ

0.14

ãĥĽ

0.13

ãĥ³ãĥĹ

0.13

usch

0.13

atty

0.13

ãģŁãĤĬ

0.13

Activations Density 0.054%

references to articles and their metadata

No Comments

No Known Activations