© 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. 15-RESID-POST-AA
    11. 86891
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transmission
    -0.07
     projects
    -0.06
     knitting
    -0.06
     CAMERA
    -0.06
     headers
    -0.06
    wicklung
    -0.06
    .student
    -0.06
     sustaining
    -0.06
     draggable
    -0.06
    ool
    -0.06
    POSITIVE LOGITS
    _agg
    0.09
     раді
    0.07
    ンス
    0.07
     karş
    0.06
    ese
    0.06
     nom
    0.06
    font
    0.06
     dm
    0.06
    mark
    0.06
    _SUR
    0.06
    Activations Density 0.026%

    No Known Activations