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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 124980
    Prev
    Next
    INDEX
    Explanations

    femur anatomy

    np_max-act · gemini-2.0-flash

    The neuron activates on anatomical terms naming specific knee joint components (e.g., femoral, tibial, condyles, patellar).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    _mar
    -0.07
    IIIK
    -0.06
    _curve
    -0.06
     Nan
    -0.06
    所以
    -0.06
    écial
    -0.06
    arakter
    -0.06
    oksen
    -0.06
    αιν
    -0.06
    stress
    -0.06
    POSITIVE LOGITS
     Лит
    0.07
     Jazeera
    0.07
     Mountain
    0.07
     Writes
    0.06
    :UI
    0.06
     今
    0.06
    ofday
    0.06
    Streaming
    0.06
    57
    0.06
     estim
    0.06
    Activations Density 0.008%

    No Known Activations