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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12168
    Prev
    Next
    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash

    The neuron activates on the model’s own role label token (e.g. “assistant”).

    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
    ogenic
    -0.07
    _dataset
    -0.06
     pets
    -0.06
    ita
    -0.06
    icals
    -0.06
     Karachi
    -0.06
    Pets
    -0.06
     Churchill
    -0.06
    Task
    -0.06
    <Button
    -0.06
    POSITIVE LOGITS
     ваг
    0.06
    uuml
    0.06
     tzv
    0.06
     техні
    0.06
     svo
    0.06
    _SELF
    0.06
     prenatal
    0.06
    叫
    0.06
     etmiş
    0.06
    _within
    0.06
    Activations Density 0.040%

    No Known Activations