INDEX

Explanations

elements related to classification and rule creation in a structured format

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

 prosec

-0.14

ILER

-0.14

uka

-0.14

 organ

-0.14

IFA

-0.14

Val

-0.13

EMU

-0.13

çķ¥

-0.13

wins

-0.13

 Vall

-0.13

POSITIVE LOGITS

Ä±rak

0.15

indh

0.15

esto

0.14

zet

0.14

ambi

0.14

achts

0.13

å©Ĩ

0.13

argas

0.13

.Transactional

0.13

ooth

0.13

Activations Density 0.069%

elements related to classification and rule creation in a structured format

No Comments

No Known Activations