Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 122266
    Prev
    Next
    INDEX
    Explanations

    Court cases

    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
     Interpret
    -0.07
    MainThread
    -0.07
    irm
    -0.07
     intestine
    -0.07
    owntown
    -0.07
    ptime
    -0.07
    _formatter
    -0.06
     光
    -0.06
    lish
    -0.06
     detectors
    -0.06
    POSITIVE LOGITS
    ]{
    0.08
    .addItem
    0.07
    ayı
    0.06
     shouted
    0.06
    	users
    0.06
     syncing
    0.06
    (filtered
    0.06
    	align
    0.06
     Says
    0.06
    capt
    0.05
    Activations Density 0.011%

    No Known Activations