© 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. 19817
    Prev
    Next
    INDEX
    Explanations

    narratives

    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
     практически
    -0.06
    ornment
    -0.06
     fra
    -0.06
    _MT
    -0.06
     bảo
    -0.06
     pioneered
    -0.06
     tarafından
    -0.06
     погод
    -0.06
    支援
    -0.06
     条
    -0.06
    POSITIVE LOGITS
    提高
    0.07
     higher
    0.07
     už
    0.07
    uant
    0.07
     Higher
    0.06
    MHz
    0.06
    лер
    0.06
    cmath
    0.06
    lico
    0.06
     tore
    0.06
    Activations Density 0.026%

    No Known Activations