© 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. 58997
    Prev
    Next
    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash

    This neuron detects programming source‐code constructs such as preprocessor directives (#include, #import), class/namespace declarations, and other code‐specific tokens.

    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
    .le
    -0.07
     Aren
    -0.06
     Counsel
    -0.06
    تبة
    -0.06
    νά
    -0.06
    _threads
    -0.06
     verir
    -0.06
    /legal
    -0.06
    Actions
    -0.06
     이용
    -0.06
    POSITIVE LOGITS
     primera
    0.07
     poet
    0.07
    스터
    0.07
    ्शन
    0.06
    'int
    0.06
    	org
    0.06
     wire
    0.06
    Encoder
    0.06
    Immediate
    0.06
    ‘
    0.06
    Activations Density 0.011%

    No Known Activations