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. 15-RESID-POST-AA
    6. 901
    Prev
    Next
    INDEX
    Explanations

    Reduces/reduction

    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
     conf
    -0.08
    install
    -0.07
     secre
    -0.07
    _related
    -0.06
     juvenile
    -0.06
    ijo
    -0.06
     такое
    -0.06
     toned
    -0.06
    _tokens
    -0.06
     classifiers
    -0.06
    POSITIVE LOGITS
     <
    0.07
     відч
    0.07
    athy
    0.07
    ुपए
    0.06
     Traits
    0.06
    Spi
    0.06
    TRANS
    0.06
     jou
    0.06
     एप
    0.06
     Gay
    0.06
    Activations Density 0.030%

    No Known Activations