© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 91842
    Prev
    Next
    INDEX
    Explanations

    adsorption/filtering

    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
    DataFrame
    -0.08
    _full
    -0.06
     forge
    -0.06
    Snippet
    -0.06
    Ст
    -0.06
     цвет
    -0.06
    erp
    -0.06
    datos
    -0.06
    交流
    -0.06
    =open
    -0.06
    POSITIVE LOGITS
    lak
    0.07
    celed
    0.07
     nation
    0.07
    �a
    0.07
    kin
    0.06
    allax
    0.06
     frat
    0.06
    松
    0.06
    cosity
    0.06
     PORT
    0.06
    Activations Density 0.048%

    No Known Activations