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. 11-RESID-POST-AA
    6. 36216
    Prev
    Next
    INDEX
    Explanations

    discipline

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ein
    -0.08
    semantic
    -0.07
     آل
    -0.07
    .energy
    -0.06
    vey
    -0.06
     Nash
    -0.06
    樣
    -0.06
     зд
    -0.06
    .userid
    -0.06
    ords
    -0.06
    POSITIVE LOGITS
    ıda
    0.07
     underway
    0.06
    ''.
    0.06
    .appendChild
    0.06
    τητα
    0.06
     Ae
    0.06
    .RegularExpressions
    0.06
     WILL
    0.06
    -live
    0.06
    เวลา
    0.06
    Activations Density 0.043%

    No Known Activations