© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 102183
    Prev
    Next
    INDEX
    Explanations

    drive

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plac
    -0.07
     selector
    -0.07
     palace
    -0.07
     nec
    -0.07
     Rac
    -0.06
     lấy
    -0.06
     speculated
    -0.06
     nuclear
    -0.06
     alternating
    -0.06
    aaa
    -0.06
    POSITIVE LOGITS
     driven
    0.12
     drive
    0.11
     driving
    0.11
     Drive
    0.10
    -driven
    0.09
    driver
    0.09
    Drive
    0.09
     Driving
    0.09
    -driving
    0.09
     driver
    0.09
    Activations Density 0.034%

    No Known Activations