© 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. 3-RESID-POST-AA
    11. 123077
    Prev
    Next
    INDEX
    Explanations

    [

    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
    :$
    -0.07
     利
    -0.06
     Aus
    -0.06
    ury
    -0.06
    semester
    -0.06
    onis
    -0.06
     Indianapolis
    -0.06
    EZ
    -0.06
    des
    -0.06
     düz
    -0.06
    POSITIVE LOGITS
     [
    0.08
    ิดต
    0.07
    AndView
    0.07
    parseInt
    0.07
    ymbol
    0.06
    .Remote
    0.06
    Figure
    0.06
    -footer
    0.06
    '].'/
    0.06
     [[
    0.06
    Activations Density 0.063%

    No Known Activations