© 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. 39107
    Prev
    Next
    INDEX
    Explanations

    parentheses/brackets

    np_max-act · gemini-2.0-flash

    The neuron triggers on chemical formula or reagent abbreviations—i.e. short uppercase‐and‐digit sequences like solvent names (DMF), ligand acronyms (BDC, HPIP), and simple molecular formulas (H₂O).

    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
     넘
    -0.07
    	thread
    -0.06
    унк
    -0.06
    Tester
    -0.06
    _Comm
    -0.06
    _pushButton
    -0.06
     zx
    -0.06
    hy
    -0.06
    두
    -0.06
    eton
    -0.06
    POSITIVE LOGITS
     plagiar
    0.07
    >`
    0.07
    疗
    0.06
     Telerik
    0.06
    .','
    0.06
     Gather
    0.06
     Ready
    0.06
    |`↵
    0.06
    >Welcome
    0.06
     competed
    0.06
    Activations Density 0.021%

    No Known Activations