© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 23200
    Prev
    Next
    INDEX
    Explanations

    дан

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     altijd
    -0.07
    Wait
    -0.07
    ：“
    -0.06
    ultip
    -0.06
    ，把
    -0.06
    Sibling
    -0.06
     Sweat
    -0.06
    icas
    -0.06
    IVED
    -0.06
    едж
    -0.06
    POSITIVE LOGITS
     дан
    0.09
     DDS
    0.07
    dG
    0.06
    attach
    0.06
     form
    0.06
    CartItem
    0.06
    manager
    0.06
     eth
    0.06
     해당
    0.06
     Form
    0.06
    Activations Density 0.004%

    No Known Activations