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. 11-RESID-POST-AA
    6. 53499
    Prev
    Next
    INDEX
    Explanations

    or

    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
     Health
    -0.08
    issance
    -0.08
    VERRIDE
    -0.07
    لاث
    -0.07
     HEALTH
    -0.07
     development
    -0.07
    _driver
    -0.07
     health
    -0.07
    ste
    -0.07
    าภ
    -0.07
    POSITIVE LOGITS
     or
    0.25
     Or
    0.17
    -or
    0.15
     OR
    0.15
    or
    0.15
    /or
    0.13
    Or
    0.13
    —or
    0.12
    _or
    0.12
     nor
    0.12
    Activations Density 0.358%

    No Known Activations