© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 1645
    Prev
    Next
    INDEX
    Explanations

    Scientific research papers

    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
    LabelText
    -0.07
    '])?
    -0.07
    <Response
    -0.07
     "?
    -0.06
    ?",
    -0.06
    รค
    -0.06
     таблиц
    -0.06
     kingdoms
    -0.06
    ?”
    -0.06
    _metrics
    -0.06
    POSITIVE LOGITS
    Andre
    0.07
    兰
    0.07
    VES
    0.06
    /*↵
    0.06
     chem
    0.06
     exh
    0.06
    reve
    0.06
     madre
    0.06
    lon
    0.06
     اصفهان
    0.06
    Activations Density 0.010%

    No Known Activations