© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 53245
    Prev
    Next
    INDEX
    Explanations

    ometer

    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
    审核
    -0.08
    							 
    -0.07
    -buffer
    -0.07
     هند
    -0.07
     прем
    -0.06
    emouth
    -0.06
    арі
    -0.06
    urface
    -0.06
     selecion
    -0.06
     AREA
    -0.06
    POSITIVE LOGITS
    plusplus
    0.07
     Н
    0.06
    .GetChild
    0.06
    _Up
    0.06
    xfd
    0.06
     [=
    0.06
    [:]↵
    0.06
    Vu
    0.06
    Know
    0.06
     uč
    0.06
    Activations Density 0.002%

    No Known Activations