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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55489
    Prev
    Next
    INDEX
    Explanations

    companies/URLs

    np_max-act · gemini-2.0-flash

    This neuron is sensitive to short alphanumeric lab‐facility identifiers (e.g. strings like “J MC LAB”).

    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
    اهی
    -0.07
     denom
    -0.06
    ystone
    -0.06
     ftp
    -0.06
     auditor
    -0.06
     Nacional
    -0.06
    /gif
    -0.06
     giochi
    -0.06
    _lambda
    -0.06
    Entries
    -0.06
    POSITIVE LOGITS
    ुर
    0.07
     undergoing
    0.06
     Дон
    0.06
     $(".
    0.06
     Grey
    0.06
    横
    0.06
     Kis
    0.06
    isActive
    0.06
    ."'
    0.06
     इसक
    0.06
    Activations Density 0.030%

    No Known Activations