© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 36210
    Prev
    Next
    INDEX
    Explanations

    many

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .uf
    -0.07
    -performance
    -0.07
     работ
    -0.07
     destroying
    -0.07
    Locker
    -0.06
    _similarity
    -0.06
     Disorders
    -0.06
    izzlies
    -0.06
    raz
    -0.06
    fake
    -0.06
    POSITIVE LOGITS
    _generated
    0.06
    =__
    0.06
    Cb
    0.06
     distortion
    0.06
    Uses
    0.06
    izontally
    0.06
    toHaveBeenCalledTimes
    0.06
    (e
    0.06
     payload
    0.05
     стало
    0.05
    Activations Density 0.057%

    No Known Activations