INDEX

Explanations

code/technical documentation

np_max-act · gemini-2.0-flash

This neuron activates on asterisks used as formatting markers (e.g. section headers and bullet points).

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

 firmware

-0.07

spam

-0.07

_under

-0.07

 correlated

-0.07

 Rivers

-0.06

 contract

-0.06

.Server

-0.06

control

-0.06

_REPO

-0.06

element

-0.06

POSITIVE LOGITS

Hod

0.07

 Οι

0.06

 другие

0.06

ัดส

0.06

 safeg

0.06

 Franken

0.06

 Offer

0.06

_employee

0.06

 extraordinarily

0.06

']")↵

0.06

Activations Density 0.050%

code/technical documentation

This neuron activates on asterisks used as formatting markers (e.g. section headers and bullet points).

No Comments

No Known Activations