© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 256
    Prev
    Next
    INDEX
    Explanations

    has

    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
    661
    -0.07
    Transformation
    -0.06
    Exceptions
    -0.06
     blobs
    -0.06
     Mint
    -0.06
     cylindrical
    -0.06
    Pří
    -0.06
     jer
    -0.06
     Worse
    -0.06
     lam
    -0.06
    POSITIVE LOGITS
     ))↵
    0.09
     ⌒
    0.07
    _MAJOR
    0.06
    .,
    0.06
     JAXB
    0.06
     veut
    0.06
    ился
    0.06
     dokonce
    0.06
     чин
    0.06
    utive
    0.06
    Activations Density 0.063%

    No Known Activations