© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 126980
    Prev
    Next
    INDEX
    Explanations

    Multiple possibilities

    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
     Ezek
    -0.06
    rical
    -0.06
     шах
    -0.06
    xff
    -0.06
    (unit
    -0.06
    igeria
    -0.06
    ráci
    -0.06
     между
    -0.06
    .tables
    -0.06
    lake
    -0.06
    POSITIVE LOGITS
     endured
    0.07
     jardin
    0.06
    _paid
    0.06
    (country
    0.06
     особливо
    0.06
    っても
    0.06
     prostě
    0.06
     findById
    0.06
     fauna
    0.06
    етель
    0.06
    Activations Density 0.043%

    No Known Activations