© 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. 109117
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash

    The neuron is primarily activated by words describing physical fitness or athletic attributes and activities.

    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
    Limits
    -0.07
     km
    -0.06
     king
    -0.06
     보
    -0.06
    짓
    -0.06
    atives
    -0.06
     ilişk
    -0.06
    참
    -0.06
    pv
    -0.06
     spectro
    -0.06
    POSITIVE LOGITS
    kube
    0.06
     mơ
    0.06
    ??↵↵
    0.06
    *math
    0.06
     pantalla
    0.06
    ूज
    0.06
    たちの
    0.06
    ैत
    0.06
    bulan
    0.06
    ΙΑΣ
    0.06
    Activations Density 0.086%

    No Known Activations