© 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. 58582
    Prev
    Next
    INDEX
    Explanations

    resource production

    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
     Spect
    -0.06
     dejtingsaj
    -0.06
    dives
    -0.06
    reason
    -0.06
     Worksheets
    -0.06
     nao
    -0.06
    conc
    -0.06
    dyž
    -0.06
    link
    -0.06
     SingleChildScrollView
    -0.05
    POSITIVE LOGITS
    .operator
    0.07
     Mezi
    0.06
    .Option
    0.06
     масс
    0.06
     §§
    0.06
     quotient
    0.06
     Peb
    0.06
     غذ
    0.06
     міста
    0.06
    .Inf
    0.06
    Activations Density 0.069%

    No Known Activations