© 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. 86350
    Prev
    Next
    INDEX
    Explanations

    headphones

    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
    Government
    -0.07
    ctxt
    -0.07
    ,s
    -0.06
    Risk
    -0.06
    (turn
    -0.06
    SEQUENTIAL
    -0.06
    -validator
    -0.06
     活
    -0.06
     tính
    -0.06
    _OK
    -0.06
    POSITIVE LOGITS
     headphones
    0.08
     lille
    0.07
    нут
    0.07
     LG
    0.06
    entarios
    0.06
     géné
    0.06
     Brake
    0.06
    enguins
    0.06
    ":"/
    0.06
    whole
    0.06
    Activations Density 0.006%

    No Known Activations