© 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. 27-RESID-POST-AA
    6. 33697
    Prev
    Next
    INDEX
    Explanations

    License

    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
     titles
    -0.06
    &m
    -0.06
    istan
    -0.06
     matt
    -0.06
     lửa
    -0.06
     Ford
    -0.06
    ชอบ
    -0.06
     kanı
    -0.05
    dw
    -0.05
     藤
    -0.05
    POSITIVE LOGITS
     endangered
    0.07
     ipsum
    0.07
    ั้
    0.07
     ">"
    0.07
    _CLICK
    0.07
     desirable
    0.06
    .Class
    0.06
     THPT
    0.06
    .Pre
    0.06
     QFont
    0.06
    Activations Density 0.002%

    No Known Activations