© 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. 19-RESID-POST-AA
    11. 109452
    Prev
    Next
    INDEX
    Explanations

    reconstruct

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Severity
    -0.08
    opak
    -0.07
     місті
    -0.07
    &e
    -0.07
     Socorro
    -0.07
    ิตภ
    -0.06
    acements
    -0.06
    piry
    -0.06
     товар
    -0.06
     Suriye
    -0.06
    POSITIVE LOGITS
     Reconstruction
    0.10
     reconstruction
    0.08
     rebuild
    0.08
     rebuilding
    0.07
    builtin
    0.07
     guessing
    0.07
     DAC
    0.06
     robot
    0.06
     rebuilt
    0.06
     fossil
    0.06
    Activations Density 0.007%

    No Known Activations