© 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. 108913
    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_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
    Answers
    -0.07
     sur
    -0.07
    ksen
    -0.07
     DRM
    -0.07
    XPath
    -0.06
     конца
    -0.06
    埋
    -0.06
    _alarm
    -0.06
    Fax
    -0.06
    Dirty
    -0.06
    POSITIVE LOGITS
     moduleName
    0.08
     PO
    0.07
     Inter
    0.06
     securely
    0.06
     packing
    0.06
    982
    0.06
     bitterly
    0.06
     billeder
    0.06
    _delta
    0.06
     november
    0.06
    Activations Density 0.013%

    No Known Activations