INDEX

Explanations

whatever

np_max-act · gemini-2.0-flash

The neuron spikes on the word “whatever.”

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 radial

-0.07

 ranks

-0.07

aup

-0.07

ด

-0.07

涨

-0.07

On

-0.06

氧

-0.06

radius

-0.06

альная

-0.06

POSITIVE LOGITS

 Whatever

0.14

 whatever

0.13

Whatever

0.12

whatever

0.11

atever

0.09

 wherever

0.09

 whichever

0.09

 whatsoever

0.09

 whoever

0.09

 whenever

0.09

Activations Density 0.008%

whatever

The neuron spikes on the word “whatever.”

No Comments

No Known Activations