© 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. 3-RESID-POST-AA
    6. 121837
    Prev
    Next
    INDEX
    Explanations

    SQL select statement

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rock
    -0.07
    /ubuntu
    -0.06
    612
    -0.06
     juven
    -0.06
     musicians
    -0.06
    (console
    -0.06
     openings
    -0.06
     Bulletin
    -0.06
    _thumb
    -0.06
     surveys
    -0.06
    POSITIVE LOGITS
     ヽ
    0.07
     quieres
    0.06
     νο
    0.06
    ehen
    0.06
     verw
    0.06
    /menu
    0.06
     Donald
    0.06
    ){//
    0.06
     advocating
    0.06
     GetString
    0.06
    Activations Density 0.518%

    No Known Activations