© 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. 19-RESID-POST-AA
    11. 114001
    Prev
    Next
    INDEX
    Explanations

    exemplo

    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
     adjective
    -0.06
    -0.06
     опред
    -0.06
     Suffolk
    -0.06
     eval
    -0.06
    delete
    -0.06
    OVID
    -0.06
     ihtiy
    -0.06
     Stokes
    -0.06
     تحلیل
    -0.06
    POSITIVE LOGITS
     ^=
    0.07
     Lebanese
    0.07
    .webdriver
    0.07
     prostě
    0.07
     upscale
    0.06
    ματος
    0.06
     generosity
    0.06
    .rate
    0.06
    ція
    0.06
    给
    0.06
    Activations Density 0.018%

    No Known Activations