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. 7-RESID-POST-AA
    6. 111625
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     we
    -0.07
     Herbert
    -0.07
     앨
    -0.07
    acz
    -0.07
    _ag
    -0.07
    Our
    -0.07
     bugün
    -0.06
     Ag
    -0.06
    bagai
    -0.06
     ederek
    -0.06
    POSITIVE LOGITS
    .tbl
    0.07
     his
    0.07
     their
    0.06
     they
    0.06
    ']=$
    0.06
     They
    0.06
    /screens
    0.06
     Their
    0.06
    genres
    0.06
    utin
    0.06
    Activations Density 0.365%

    No Known Activations