© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56696
    Prev
    Next
    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash

    The neuron responds to regex digit‐count quantifiers—i.e. occurrences of “\d{N}” where N is a small number (e.g. 2, 3, or 4).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    Muon
    -0.07
     Red
    -0.06
    ῆ
    -0.06
    _reviews
    -0.06
    finger
    -0.06
     desert
    -0.06
     Kristen
    -0.06
    .findall
    -0.06
     Hands
    -0.06
    _descr
    -0.06
    POSITIVE LOGITS
    痛
    0.07
     courte
    0.07
    !,↵
    0.07
    :mysql
    0.07
    [b
    0.07
    -il
    0.07
    Republic
    0.06
     площад
    0.06
     daunting
    0.06
    ?,
    0.06
    Activations Density 0.004%

    No Known Activations