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. 19-RESID-POST-AA
    6. 9926
    Prev
    Next
    INDEX
    Explanations

    explainable machine learning

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    員
    -0.06
    장이
    -0.06
    _fac
    -0.06
    熊
    -0.06
     дет
    -0.06
    LoggedIn
    -0.05
    <_
    -0.05
     Arb
    -0.05
    Attend
    -0.05
    Emoji
    -0.05
    POSITIVE LOGITS
     zlat
    0.08
    .Transfer
    0.07
    .",↵
    0.07
     ขนาด
    0.07
    weed
    0.07
     визначення
    0.07
     financially
    0.06
    =index
    0.06
    ุตสาห
    0.06
    /class
    0.06
    Activations Density 0.025%

    No Known Activations