INDEX

Explanations

technical terminology related to engine operation and maintenance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

åĪº

-0.14

 Sink

-0.14

 Winds

-0.14

 soll

-0.14

arser

-0.13

 ÏĢÎ±ÏģÎ¬

-0.13

 Cement

-0.13

à¸łà¸²à¸ŀ

-0.13

keit

-0.13

cripts

-0.13

POSITIVE LOGITS

apor

0.19

 expanded

0.18

cav

0.18

 seize

0.17

 expand

0.17

 seized

0.16

 boil

0.16

 expanding

0.16

 seizure

0.16

 contamination

0.16

Activations Density 0.016%

technical terminology related to engine operation and maintenance

No Comments

No Known Activations