INDEX

Explanations

academic affiliations and qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

emailer

-0.16

sonian

-0.16

 Sweden

-0.15

Ã¼st

-0.15

á»Ľ

-0.14

steller

-0.14

Sweden

-0.14

 Gros

-0.14

parator

-0.14

 menn

-0.14

POSITIVE LOGITS

 forsk

0.20

 Centre

0.17

 habil

0.17

PhD

0.16

VIN

0.16

Arb

0.16

Ui

0.15

 Campus

0.15

.OR

0.15

 Bachelor

0.15

Activations Density 0.011%

academic affiliations and qualifications

No Comments

No Known Activations