Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 99897
    Prev
    Next
    INDEX
    Explanations

    with

    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
    ζ
    -0.07
    那个
    -0.06
    خان
    -0.06
     shootout
    -0.06
     arac
    -0.06
    pedia
    -0.06
     haben
    -0.06
    遍
    -0.06
     brief
    -0.06
    .isLoggedIn
    -0.06
    POSITIVE LOGITS
    perse
    0.08
    arb
    0.07
    ücü
    0.07
    SCRI
    0.06
    event
    0.06
     volum
    0.06
     aug
    0.06
    _PAY
    0.06
     Montana
    0.06
     resulting
    0.06
    Activations Density 0.018%

    No Known Activations