© 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. 39202
    Prev
    Next
    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are part of structured code documentation comments (e.g. the leading “*” markers and Doxygen‐style tags like “@brief”).

    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
    .hist
    -0.06
     gums
    -0.06
     perpetual
    -0.06
     виде
    -0.06
    　ノ
    -0.06
     sampler
    -0.06
    Ral
    -0.06
     loginUser
    -0.06
     rampant
    -0.06
     Variables
    -0.06
    POSITIVE LOGITS
    iston
    0.07
    τρα
    0.07
    orta
    0.07
    RTL
    0.06
    ELL
    0.06
    composer
    0.06
    esda
    0.06
     Woods
    0.06
    _plane
    0.06
    andles
    0.06
    Activations Density 0.005%

    No Known Activations