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. 110653
    Prev
    Next
    INDEX
    Explanations

    "<"

    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
    (sentence
    -0.07
     glass
    -0.07
     Creek
    -0.07
    //@
    -0.06
     здоб
    -0.06
    -touch
    -0.06
    将
    -0.06
    .YEAR
    -0.06
    Descripcion
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     PropertyInfo
    0.07
    /power
    0.07
    ,'\
    0.07
    fdb
    0.06
     складі
    0.06
    +-+-+-+-
    0.06
     modal
    0.05
    _strike
    0.05
     contrato
    0.05
    _register
    0.05
    Activations Density 0.019%

    No Known Activations