© 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. 122208
    Prev
    Next
    INDEX
    Explanations

    Various kinds of "systems"

    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
     your
    -0.07
    γι
    -0.06
     reversible
    -0.06
    lg
    -0.06
    oreferrer
    -0.06
    my
    -0.06
    替
    -0.06
    ublisher
    -0.06
     tantal
    -0.06
     Technician
    -0.06
    POSITIVE LOGITS
     Alla
    0.07
    edik
    0.07
    ardon
    0.07
    .characters
    0.06
    arah
    0.06
    KindOfClass
    0.06
    orrh
    0.06
     arr
    0.06
     Tree
    0.06
    wishlist
    0.06
    Activations Density 0.184%

    No Known Activations