© 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. 46102
    Prev
    Next
    INDEX
    Explanations

    Arrays of data

    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
     통
    -0.06
     Catholics
    -0.06
     rope
    -0.06
    .Qt
    -0.06
     mating
    -0.06
    _ORDER
    -0.06
    、この
    -0.06
     хоч
    -0.06
     prestige
    -0.06
     Wilhelm
    -0.06
    POSITIVE LOGITS
     Patch
    0.07
    <=
    0.07
    lá
    0.07
    .URL
    0.07
    ­i
    0.06
    ações
    0.06
     voi
    0.06
    مح
    0.06
    236
    0.06
     أعلام
    0.06
    Activations Density 0.102%

    No Known Activations