© 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. 113390
    Prev
    Next
    INDEX
    Explanations

    includes

    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
     Pope
    -0.08
    また
    -0.06
    .orig
    -0.06
    _ready
    -0.06
     此
    -0.06
     cunning
    -0.06
    alamat
    -0.06
    ier
    -0.06
     ним
    -0.06
    _()↵
    -0.06
    POSITIVE LOGITS
     SOL
    0.07
     COPYING
    0.07
     MLP
    0.07
     ►
    0.06
    ジア
    0.06
     GRAPH
    0.06
    .TextAlignment
    0.06
     compuls
    0.06
    BEST
    0.06
    elian
    0.06
    Activations Density 0.142%

    No Known Activations