© 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. 91137
    Prev
    Next
    INDEX
    Explanations

    clinical reference values/methods

    np_max-act · gemini-2.0-flash

    The neuron activates on technical noun phrases naming tools or mechanisms—e.g. “mnemonic device” or “reward function.”

    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
     feedback
    -0.06
     rect
    -0.06
     Classic
    -0.06
    “Well
    -0.06
     determines
    -0.06
     ostr
    -0.06
     Ster
    -0.06
     occup
    -0.06
     billions
    -0.06
     theoret
    -0.06
    POSITIVE LOGITS
    beits
    0.07
    _Format
    0.07
    ченко
    0.07
    国の
    0.07
    mür
    0.06
     웹사이트
    0.06
    iš
    0.06
    ;'>
    0.06
     neod
    0.06
    .HttpSession
    0.06
    Activations Density 0.150%

    No Known Activations