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. 100506
    Prev
    Next
    INDEX
    Explanations

    chart

    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
     lawyers
    -0.08
     centre
    -0.07
     browse
    -0.07
    _ray
    -0.07
     newspaper
    -0.06
    -trash
    -0.06
    (wp
    -0.06
    _PO
    -0.06
     nerd
    -0.06
     packing
    -0.06
    POSITIVE LOGITS
    634
    0.07
     Kath
    0.07
    ヶ
    0.07
    भ
    0.06
     Conj
    0.06
    /H
    0.06
    elems
    0.06
    endants
    0.06
     kommer
    0.06
     پیچ
    0.06
    Activations Density 0.031%

    No Known Activations