© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 104793
    Prev
    Next
    INDEX
    Explanations

    increasing limits

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wind
    -0.07
     जर
    -0.07
    置
    -0.06
     порядок
    -0.06
    чен
    -0.06
     профилакти
    -0.06
     ace
    -0.06
     осуществ
    -0.06
     вплив
    -0.06
    agento
    -0.06
    POSITIVE LOGITS
    _trim
    0.07
    (None
    0.07
    _LIMIT
    0.07
    cw
    0.07
    .getX
    0.06
    /story
    0.06
     hObject
    0.06
    FXML
    0.06
     Vill
    0.06
    있
    0.06
    Activations Density 0.019%

    No Known Activations