© 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. 60422
    Prev
    Next
    INDEX
    Explanations

    analysis

    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
     Mesh
    -0.06
    arial
    -0.06
    子的
    -0.06
    hawk
    -0.06
    ACHED
    -0.06
     Circular
    -0.06
    ص
    -0.06
     dropdown
    -0.06
    estone
    -0.06
    ourney
    -0.06
    POSITIVE LOGITS
    _services
    0.07
     tt
    0.07
     NSAttributedString
    0.07
     WTO
    0.06
     jc
    0.06
    .Maybe
    0.06
    ,,,
    0.06
    angep
    0.06
    .extra
    0.06
    	tc
    0.06
    Activations Density 0.000%

    No Known Activations