© 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. 86753
    Prev
    Next
    INDEX
    Explanations

    future predictions

    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
    .Byte
    -0.07
    .Build
    -0.06
    tir
    -0.06
     ucz
    -0.06
     Archer
    -0.06
     automation
    -0.06
    /if
    -0.06
     photoc
    -0.06
     vzděl
    -0.06
     AR
    -0.06
    POSITIVE LOGITS
    ihanna
    0.07
     bracket
    0.07
    ossa
    0.06
    aju
    0.06
    rious
    0.06
    ;<
    0.06
    豆
    0.06
     retorna
    0.06
    educated
    0.06
    brit
    0.06
    Activations Density 0.093%

    No Known Activations