Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 9972
    Prev
    Next
    INDEX
    Explanations

    on

    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
    Highlights
    -0.07
     Banc
    -0.06
    venes
    -0.06
    Rich
    -0.06
    _vertical
    -0.06
     dicks
    -0.06
    CppClass
    -0.06
    )r
    -0.06
    ToUpper
    -0.06
     LIN
    -0.06
    POSITIVE LOGITS
     sow
    0.07
    .abstract
    0.06
    .Registry
    0.06
     deriving
    0.06
    [--
    0.06
     происходит
    0.06
    osoph
    0.06
     passionately
    0.06
    /ag
    0.06
     newItem
    0.06
    Activations Density 0.025%

    No Known Activations