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. 3-RESID-POST-AA
    6. 122102
    Prev
    Next
    INDEX
    Explanations

    possessive "'s"

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     حال
    -0.08
    ographers
    -0.07
    ौकर
    -0.07
    /animations
    -0.06
    especially
    -0.06
    named
    -0.06
    orig
    -0.06
    _orig
    -0.06
    places
    -0.06
    意义
    -0.06
    POSITIVE LOGITS
    (sim
    0.06
    ichte
    0.06
    Browse
    0.06
    crc
    0.06
    .cam
    0.06
    öl
    0.06
    Merc
    0.06
     Dol
    0.06
     Hex
    0.06
     deed
    0.06
    Activations Density 0.011%

    No Known Activations