Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 53502
    Prev
    Next
    INDEX
    Explanations

    success

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appar
    -0.07
    InstantiationException
    -0.07
    _INC
    -0.07
    CompanyId
    -0.07
     prefers
    -0.06
     исход
    -0.06
    χ
    -0.06
    ۲۰
    -0.06
     attacked
    -0.06
     Mısır
    -0.06
    POSITIVE LOGITS
    urous
    0.07
    _journal
    0.06
    AuthToken
    0.06
    ेयर
    0.06
    驾
    0.06
    ENDOR
    0.06
    (eq
    0.06
    vature
    0.06
     Curve
    0.06
     hlavu
    0.06
    Activations Density 0.146%

    No Known Activations