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. 128913
    Prev
    Next
    INDEX
    Explanations

    network

    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
     этого
    -0.07
    getitem
    -0.07
    ismic
    -0.06
    .translate
    -0.06
     attaches
    -0.06
    /MM
    -0.06
    adjusted
    -0.06
    -cat
    -0.06
    (storage
    -0.06
    звичай
    -0.06
    POSITIVE LOGITS
    layout
    0.07
    ทางการ
    0.07
    )];↵
    0.06
     liberals
    0.06
     breadcrumb
    0.06
    �
    0.06
    endoza
    0.06
     Dre
    0.06
    [next
    0.06
     ★
    0.06
    Activations Density 0.002%

    No Known Activations