INDEX

Explanations

bos

np_max-act · gemini-2.0-flash

This neuron selectively activates on tokens related to particle‐physics discussion (e.g. “particle,” “physics,” “Standard Model,” “Higgs,” “Collider”) and on the special header‐ID markers that frame those technical sections.

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

 mega

-0.07

 ourselves

-0.07

oda

-0.07

CHAIN

-0.06

(div

-0.06

bic

-0.06

 Ελλην

-0.06

 explos

-0.06

 observer

-0.06

Words

-0.06

POSITIVE LOGITS

ocrin

0.07

Entered

0.07

 Борис

0.06

AccountId

0.06

設定

0.06

erli

0.06

	mode

0.06

 جور

0.06

그

0.06

'post

0.06

Activations Density 0.005%

bos

This neuron selectively activates on tokens related to particle‐physics discussion (e.g. “particle,” “physics,” “Standard Model,” “Higgs,” “Collider”) and on the special header‐ID markers that frame those technical sections.

No Comments

No Known Activations