© 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. 58415
    Prev
    Next
    INDEX
    Explanations

    HTTP request headers/parameters

    np_max-act · gemini-2.0-flash

    This neuron fires on Spring-style Java annotation tokens—particularly the names and argument delimiters of annotations like @RequestHeader and @PathVariable.

    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
     strokeWidth
    -0.06
     Yuk
    -0.06
    施
    -0.06
     Boots
    -0.06
    てい
    -0.06
     Lager
    -0.06
    Titan
    -0.06
     Wash
    -0.06
    .CREATED
    -0.06
    Marketing
    -0.06
    POSITIVE LOGITS
     puerto
    0.07
    ']['
    0.07
     DataAccess
    0.07
     prompted
    0.06
     '''↵
    0.06
    Implementation
    0.06
     happily
    0.06
     зуп
    0.06
     droit
    0.06
    _RESULT
    0.06
    Activations Density 0.006%

    No Known Activations