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. 73770
    Prev
    Next
    INDEX
    Explanations

    the

    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
     anda
    -0.07
     ₹
    -0.07
     виник
    -0.07
    ��
    -0.07
     handle
    -0.06
    >Z
    -0.06
     ปร
    -0.06
    FACT
    -0.06
     Anth
    -0.06
     diren
    -0.06
    POSITIVE LOGITS
    illation
    0.07
    Intersection
    0.06
     NOAA
    0.06
    ادة
    0.06
    Serializable
    0.06
    фер
    0.06
     deviceId
    0.06
    egov
    0.06
    oves
    0.06
    .Par
    0.06
    Activations Density 0.000%

    No Known Activations