INDEX

Explanations

references to maintenance and service-related terminology

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

efeller

-0.15

eyh

-0.15

avaÅŁ

-0.14

 refined

-0.13

avigator

-0.13

Retry

-0.13

vir

-0.13

etak

-0.13

ÏħÎº

-0.13

elpers

-0.13

POSITIVE LOGITS

 maintenance

0.65

 Maintenance

0.58

 maint

0.55

 repair

0.54

Maintenance

0.54

maintenance

0.53

 repairs

0.50

 maintain

0.45

 Maint

0.44

 Repair

0.44

Activations Density 0.452%

references to maintenance and service-related terminology

No Comments

No Known Activations