INDEX

Explanations

references to maintaining or keeping things operational

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

uez

-0.15

 prematurely

-0.15

æĹ©

-0.15

è¿ħ

-0.15

 early

-0.15

 instantly

-0.14

 immediately

-0.14

 prost

-0.14

POSITIVE LOGITS

 longer

0.68

 Longer

0.57

 longest

0.53

 lÃ¢u

0.31

long

0.31

 long

0.30

 LONG

0.29

-long

0.29

 dÃłi

0.28

 till

0.28

Activations Density 0.304%

references to maintaining or keeping things operational

No Comments

No Known Activations