INDEX

Explanations

mathematical and probabilistic language associated with events and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

resi

-0.15

roti

-0.15

 Feed

-0.14

 freeze

-0.14

 Compensation

-0.14

 mang

-0.14

emd

-0.14

 residuals

-0.13

idlo

-0.13

LAG

-0.13

POSITIVE LOGITS

 probability

0.40

 probabilities

0.36

 odds

0.35

probability

0.33

 Probability

0.33

 Chance

0.30

 chance

0.30

Probability

0.29

 prob

0.29

Bin

0.29

Activations Density 0.314%

mathematical and probabilistic language associated with events and outcomes

No Comments

No Known Activations

mathematical and probabilistic language associated with events and outcomes

No Comments

No Known Activations