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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21516
    Prev
    Next
    INDEX
    Explanations

    time

    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
    .SuspendLayout
    -0.07
     butto
    -0.07
     الاخ
    -0.07
    047
    -0.07
     мер
    -0.06
    [x
    -0.06
     stehen
    -0.06
    582
    -0.06
    ration
    -0.06
    _EL
    -0.06
    POSITIVE LOGITS
    BarButton
    0.07
     ammon
    0.06
     defining
    0.06
    jango
    0.06
    .DataType
    0.06
    colors
    0.06
    .virtual
    0.06
    _DIAG
    0.06
    aseña
    0.06
    WillAppear
    0.06
    Activations Density 0.153%

    No Known Activations