© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 52935
    Prev
    Next
    INDEX
    Explanations

    Realizations/discoveries

    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
    602
    -0.06
    ä
    -0.06
    وس
    -0.06
    ár
    -0.06
    743
    -0.06
    atchewan
    -0.06
     Rolex
    -0.06
     clothes
    -0.06
    .ctx
    -0.06
     creditors
    -0.06
    POSITIVE LOGITS
    .""
    0.07
    -existent
    0.07
    Mom
    0.07
     mutation
    0.06
     کنترل
    0.06
    Signup
    0.06
    lasyon
    0.06
     disponibles
    0.06
     '%'
    0.06
    .dispatch
    0.06
    Activations Density 0.096%

    No Known Activations