© 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. 58386
    Prev
    Next
    INDEX
    Explanations

    Risks

    np_max-act · gemini-2.0-flash

    This neuron detects the start‐of‐section markers and risk‐analysis terminology (e.g. header ID tags like `<|start_header_id|>` and words around “risk,” “analysis,” “identify,” “potential,” etc.).

    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
     HttpServletRequest
    -0.07
     derivatives
    -0.07
    럼
    -0.06
    린이
    -0.06
    ‌کنند
    -0.06
     altında
    -0.06
    ‌ان
    -0.06
    _on
    -0.06
     стандарт
    -0.06
    _busy
    -0.06
    POSITIVE LOGITS
     Stellar
    0.07
    aze
    0.07
     Frozen
    0.06
     evolutionary
    0.06
     DS
    0.06
     cosmic
    0.06
    marshal
    0.06
    APTER
    0.06
    taient
    0.06
    plate
    0.06
    Activations Density 0.028%

    No Known Activations