INDEX

Explanations

weight

np_max-act · gemini-2.0-flash

This neuron detects mentions of heaviness or weight (terms like “heavy,” “weight,” “mass,” “cumbersome,” etc.).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

(fmt

-0.07

Ingredient

-0.06

 relaxing

-0.06

üyük

-0.06

 pokud

-0.06

 volunteering

-0.06

_inc

-0.06

buf

-0.06

 volunteered

-0.06

vow

-0.05

POSITIVE LOGITS

_FULL

0.08

►

0.07

TI

0.06

 Nome

0.06

providers

0.06

ισμ

0.06

 Accent

0.06

 Antworten

0.06

 divis

0.06

atos

0.06

Activations Density 0.032%

weight

This neuron detects mentions of heaviness or weight (terms like “heavy,” “weight,” “mass,” “cumbersome,” etc.).

No Comments

No Known Activations