© 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. 58379
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron activates on parenthesized acronyms or abbreviations (e.g. “(FDI)”, “(DDoS)”).

    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
    minus
    -0.06
    yw
    -0.06
    .are
    -0.06
    spě
    -0.06
     scrapped
    -0.06
    observation
    -0.06
    Composition
    -0.06
     Blvd
    -0.05
    numpy
    -0.05
     Navy
    -0.05
    POSITIVE LOGITS
     FirebaseAuth
    0.07
     быстро
    0.07
    ं
    0.07
     acesso
    0.07
    >();↵
    0.07
     TempData
    0.07
    Malloc
    0.07
    房
    0.07
     configFile
    0.07
    說
    0.06
    Activations Density 0.102%

    No Known Activations