© 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. 27-RESID-POST-AA
    11. 11675
    Prev
    Next
    INDEX
    Explanations

    So

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dzi
    -0.07
    تد
    -0.07
    _lead
    -0.06
    čen
    -0.06
     Integr
    -0.06
    .moves
    -0.06
     basin
    -0.06
     Spit
    -0.06
    cede
    -0.06
    ках
    -0.06
    POSITIVE LOGITS
     соглас
    0.06
    bette
    0.06
    ClassName
    0.06
    (INVOKE
    0.06
    ερο
    0.06
    .CSS
    0.06
    ."'
    0.06
    .getBoolean
    0.06
    ňování
    0.06
    	boolean
    0.06
    Activations Density 0.026%

    No Known Activations