© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95850
    Prev
    Next
    INDEX
    Explanations

    options, open

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     název
    -0.07
     системи
    -0.07
    になった
    -0.07
     environment
    -0.06
    हर
    -0.06
    แทน
    -0.06
     continuity
    -0.06
     mandates
    -0.06
     loud
    -0.06
    ตะว
    -0.06
    POSITIVE LOGITS
    Currently
    0.07
    Ç
    0.06
     Appe
    0.06
    _ARCHIVE
    0.06
     Nz
    0.06
    А
    0.06
     Insp
    0.06
     발
    0.06
     Nothing
    0.06
     Opcode
    0.06
    Activations Density 0.161%

    No Known Activations