© 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. 11-RESID-POST-AA
    6. 77296
    Prev
    Next
    INDEX
    Explanations

    source code

    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_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
    _ta
    -0.07
    sending
    -0.07
    Numeric
    -0.07
     تحصیل
    -0.06
     TOR
    -0.06
    entina
    -0.06
     sulfate
    -0.06
    dataArray
    -0.06
     cultured
    -0.06
    <fieldset
    -0.06
    POSITIVE LOGITS
    รวจ
    0.07
     culp
    0.06
     مك
    0.06
    ้าหน
    0.06
    eldig
    0.06
     archae
    0.06
     nervous
    0.06
    irut
    0.06
     ksi
    0.06
     athe
    0.06
    Activations Density 0.057%

    No Known Activations