© 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. 27-RESID-POST-AA
    11. 8219
    Prev
    Next
    INDEX
    Explanations

    Kites

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _position
    -0.07
    Common
    -0.07
     brothers
    -0.06
    ................................................................
    -0.06
     computed
    -0.06
     댓글
    -0.06
    Uniform
    -0.06
    دي
    -0.06
    deliver
    -0.06
    -intensive
    -0.06
    POSITIVE LOGITS
     riêng
    0.07
    들을
    0.06
    istrict
    0.06
    idian
    0.06
    :d
    0.06
     scandal
    0.06
     technicians
    0.06
     transl
    0.06
    (fragment
    0.06
     khung
    0.06
    Activations Density 0.008%

    No Known Activations