© 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. 114492
    Prev
    Next
    INDEX
    Explanations

    in

    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
     także
    -0.08
     timeless
    -0.06
     spyOn
    -0.06
     bike
    -0.06
    /background
    -0.06
    doctor
    -0.06
     implying
    -0.06
     Law
    -0.06
     INCLUDING
    -0.06
     UK
    -0.06
    POSITIVE LOGITS
    -pages
    0.07
     commod
    0.06
    PARAM
    0.06
     трь
    0.06
    مش
    0.06
     Macros
    0.06
     kaf
    0.06
    .clientWidth
    0.06
     argent
    0.06
     gön
    0.06
    Activations Density 0.030%

    No Known Activations