© 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. 15-RESID-POST-AA
    11. 99455
    Prev
    Next
    INDEX
    Explanations

    improvement

    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
     لازم
    -0.07
    elpers
    -0.06
    _gradient
    -0.06
    яется
    -0.06
     अब
    -0.06
    ازم
    -0.06
     ejac
    -0.06
    iri
    -0.06
    EdgeInsets
    -0.06
     лиц
    -0.06
    POSITIVE LOGITS
    auth
    0.07
    .setBackground
    0.07
     hostility
    0.07
    arov
    0.07
    RenderingContext
    0.06
     petit
    0.06
    (cl
    0.06
     Congressional
    0.06
    tries
    0.06
     cafeteria
    0.06
    Activations Density 0.087%

    No Known Activations