© 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. 35006
    Prev
    Next
    INDEX
    Explanations

    functional

    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
     mse
    -0.07
     musí
    -0.07
     jose
    -0.06
    tech
    -0.06
     harmful
    -0.06
    _Password
    -0.06
    (SE
    -0.06
    Histogram
    -0.06
    .magnitude
    -0.06
     Spam
    -0.06
    POSITIVE LOGITS
    setSize
    0.06
    將
    0.06
    oon
    0.06
    일에
    0.06
     İyi
    0.06
    ृत
    0.06
     yılında
    0.06
    acente
    0.06
    DE
    0.05
    ấ
    0.05
    Activations Density 0.013%

    No Known Activations