© 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. 3-RESID-POST-AA
    6. 93709
    Prev
    Next
    INDEX
    Explanations

    будут

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cdot
    -0.08
     мож
    -0.07
     may
    -0.06
     Müş
    -0.06
     timeframe
    -0.06
     COMPONENT
    -0.06
     AJAX
    -0.06
     madde
    -0.06
     réal
    -0.06
     Mak
    -0.06
    POSITIVE LOGITS
     будут
    0.24
    :///
    0.10
     budou
    0.08
     будуть
    0.07
     Peanut
    0.06
    Geom
    0.06
    ěstí
    0.06
    -company
    0.06
    ές
    0.06
     peek
    0.06
    Activations Density 0.000%

    No Known Activations