© 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
    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. 56173
    Prev
    Next
    INDEX
    Explanations

    academic publications

    np_max-act · gemini-2.0-flash

    This neuron detects tokens related to mesh optimization and locality improvements (e.g. “Optimization,” “mesh,” “locality,” “caching”) in code headers or comments.

    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
    atisation
    -0.07
    /home
    -0.07
    	BOOL
    -0.07
    sockets
    -0.06
    уже
    -0.06
    .ServletException
    -0.06
     posterior
    -0.06
    Iterable
    -0.06
     '&
    -0.06
     працю
    -0.06
    POSITIVE LOGITS
     Ball
    0.07
     Ahmet
    0.06
    जर
    0.06
    erguson
    0.06
    _qp
    0.06
    classic
    0.06
    ])]
    0.06
     unitOfWork
    0.06
     Takım
    0.06
    .btnAdd
    0.06
    Activations Density 0.028%

    No Known Activations