© 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. 92168
    Prev
    Next
    INDEX
    Explanations

    from

    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
     CENT
    -0.07
    .ACTION
    -0.07
    _REPO
    -0.07
    atch
    -0.06
     taken
    -0.06
     phương
    -0.06
     dust
    -0.06
     temples
    -0.06
    .jpeg
    -0.06
    Shar
    -0.06
    POSITIVE LOGITS
    ahrung
    0.07
    妖
    0.07
    udes
    0.07
    d
    0.06
     натураль
    0.06
     JT
    0.06
     Mons
    0.06
    ्ट
    0.06
    element
    0.06
    ív
    0.06
    Activations Density 0.000%

    No Known Activations