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. 23-RESID-POST-AA
    6. 104052
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Azure
    -0.07
    .ini
    -0.07
     Purs
    -0.06
    Soon
    -0.06
     strr
    -0.06
    产品
    -0.06
     Champion
    -0.06
    ropolis
    -0.06
     rom
    -0.06
     ei
    -0.06
    POSITIVE LOGITS
     opat
    0.07
    aviours
    0.06
    .Fat
    0.06
    (driver
    0.06
     *((
    0.06
    EVENT
    0.06
    .application
    0.06
    .localizedDescription
    0.06
    .atom
    0.06
    دواج
    0.06
    Activations Density 0.005%

    No Known Activations