© 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
    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. 6837
    Prev
    Next
    INDEX
    Explanations

    Numbers in code

    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
    cot
    -0.07
    (props
    -0.07
     Cyprus
    -0.06
    Chr
    -0.06
    ANCEL
    -0.06
    ames
    -0.06
     Liz
    -0.06
    _ti
    -0.06
    asket
    -0.06
    PathVariable
    -0.06
    POSITIVE LOGITS
     seamlessly
    0.07
     spline
    0.07
     faithfully
    0.07
    커
    0.06
     weaknesses
    0.06
     đảm
    0.06
     bản
    0.06
     Acquisition
    0.06
    larından
    0.06
    اسة
    0.06
    Activations Density 0.048%

    No Known Activations