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. 90950
    Prev
    Next
    INDEX
    Explanations

    synth

    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
    -mark
    -0.07
    .statusCode
    -0.06
     Legal
    -0.06
     quantitative
    -0.06
     inmates
    -0.06
     methodology
    -0.06
     biomass
    -0.06
     Одна
    -0.06
     crust
    -0.06
    innitus
    -0.06
    POSITIVE LOGITS
    pee
    0.07
    company
    0.07
    evším
    0.06
    íny
    0.06
     «
    0.06
    (',')↵
    0.06
     competitors
    0.06
     @
    0.06
    ела
    0.06
    venir
    0.06
    Activations Density 0.001%

    No Known Activations