© 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. 15-RESID-POST-AA
    11. 33180
    Prev
    Next
    INDEX
    Explanations

    tile

    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
    =*/
    -0.06
     नक
    -0.06
    .numberOfLines
    -0.06
     Beds
    -0.06
     payroll
    -0.06
     �
    -0.05
    .Services
    -0.05
     emphasizes
    -0.05
     groundwork
    -0.05
     {%
    -0.05
    POSITIVE LOGITS
    [K
    0.08
     тел
    0.07
    ьте
    0.07
     estaba
    0.07
    ución
    0.06
    350
    0.06
     (^
    0.06
    iliar
    0.06
    Outcome
    0.06
     kultur
    0.06
    Activations Density 0.001%

    No Known Activations