© 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 EvalsExportsAPI 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. 19-RESID-POST-AA
    11. 112800
    Prev
    Next
    INDEX
    Explanations

    parenthesis

    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
     assez
    -0.06
     yarn
    -0.06
    шь
    -0.06
     <$
    -0.06
     estr
    -0.06
    .Run
    -0.06
     द
    -0.06
    contains
    -0.06
    nech
    -0.06
     sotto
    -0.06
    POSITIVE LOGITS
    .Router
    0.07
     compassion
    0.06
    ANJI
    0.06
    /language
    0.06
    .*(
    0.06
     possessions
    0.06
    ledge
    0.06
     tol
    0.06
    touch
    0.06
    -mobile
    0.06
    Activations Density 0.000%

    No Known Activations