© 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. 19-RESID-POST-AA
    6. 122140
    Prev
    Next
    INDEX
    Explanations

    ers

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sharp
    -0.07
     CID
    -0.06
     norm
    -0.06
     sketches
    -0.06
    getBlock
    -0.06
    orted
    -0.06
    longleftrightarrow
    -0.06
    ерап
    -0.06
     clears
    -0.06
     halo
    -0.06
    POSITIVE LOGITS
    /+
    0.07
    :.:.:
    0.06
    _BOUND
    0.06
    keepers
    0.06
     أنا
    0.06
    ρας
    0.06
    keeper
    0.06
    .epam
    0.06
     autorelease
    0.06
    اقتص
    0.06
    Activations Density 0.168%

    No Known Activations