© 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
    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. 9124
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    icamente
    -0.06
    vehicle
    -0.06
     geçir
    -0.06
     Medicare
    -0.06
    cação
    -0.06
    members
    -0.06
     acheter
    -0.06
    baugh
    -0.06
    ec
    -0.06
    _players
    -0.06
    POSITIVE LOGITS
    .Match
    0.08
     approached
    0.08
    "]=
    0.07
     invit
    0.07
    .ag
    0.07
    آن
    0.07
     نت
    0.07
    .extensions
    0.06
    查询
    0.06
     hints
    0.06
    Activations Density 0.021%

    No Known Activations