INDEX

Explanations

technical terms and concepts related to algorithms and data structures, particularly in the context of machine learning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

orer

-0.16

ebi

-0.16

 ModelState

-0.15

egot

-0.15

arga

-0.15

ÎŃÏģÎ³

-0.14

çīĪ

-0.14

 Lindsay

-0.14

amen

-0.14

ÐµÑĢÑĤÐ°

-0.14

POSITIVE LOGITS

sed

0.16

tet

0.14

/qu

0.14

Hag

0.14

 spread

0.14

ience

0.14

appy

0.13

spread

0.13

ayo

0.13

quan

0.13

Activations Density 0.068%

technical terms and concepts related to algorithms and data structures, particularly in the context of machine learning

No Comments

No Known Activations