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. 74866
    Prev
    Next
    INDEX
    Explanations

    on

    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
     Focus
    -0.08
     cũng
    -0.06
    eof
    -0.06
    MessageBox
    -0.06
     persecuted
    -0.06
     بسیار
    -0.06
    ionate
    -0.06
    ۰۰
    -0.06
     census
    -0.06
    (月
    -0.06
    POSITIVE LOGITS
     tông
    0.06
    ushima
    0.06
     dab
    0.06
     Regina
    0.06
    coal
    0.06
     Shim
    0.06
    Alg
    0.06
    _PICTURE
    0.06
    (([
    0.06
     dys
    0.06
    Activations Density 0.016%

    No Known Activations