© 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. 27-RESID-POST-AA
    11. 57318
    Prev
    Next
    INDEX
    Explanations

    ak

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tabela
    -0.07
    /news
    -0.07
     cylinders
    -0.07
     HLS
    -0.06
    .yaml
    -0.06
     stripes
    -0.06
    _parameter
    -0.06
     windowHeight
    -0.06
     theano
    -0.06
     ffmpeg
    -0.06
    POSITIVE LOGITS
    agos
    0.08
     POP
    0.07
    ars
    0.07
     monopol
    0.06
     कट
    0.06
     Brick
    0.06
    CustomLabel
    0.06
    ARS
    0.06
     confisc
    0.06
    حي
    0.06
    Activations Density 0.002%

    No Known Activations