© 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 EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 45144
    Prev
    Next
    INDEX
    Explanations

    is

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /report
    -0.06
    -St
    -0.06
    -New
    -0.06
     AttributeError
    -0.06
    Those
    -0.06
     Parent
    -0.06
    Emergency
    -0.06
    -service
    -0.06
    .deepEqual
    -0.06
    Services
    -0.06
    POSITIVE LOGITS
     пів
    0.07
     AUTO
    0.07
    orelease
    0.07
     offended
    0.07
    答
    0.06
    ific
    0.06
    valueOf
    0.06
    kám
    0.06
     misleading
    0.06
     uygu
    0.06
    Activations Density 0.107%

    No Known Activations