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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58642
    Prev
    Next
    INDEX
    Explanations

    aneurysms

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of endovascular repair of abdominal aortic aneurysms (e.g. EVAR, stent-graft procedures).

    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
    างว
    -0.07
     Malta
    -0.07
     발
    -0.07
    fv
    -0.06
     contrad
    -0.06
     tantra
    -0.06
     bậc
    -0.06
     není
    -0.06
    Contr
    -0.06
    con
    -0.06
    POSITIVE LOGITS
    이는
    0.07
     자동
    0.06
     usefulness
    0.06
    device
    0.06
     detector
    0.06
    udem
    0.06
     drinking
    0.06
     hitch
    0.06
     Dairy
    0.06
     acceptable
    0.06
    Activations Density 0.005%

    No Known Activations