© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58643
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    This neuron activates on include paths for the Linux sound subsystem (e.g. “sound/core.h”, “sound/pcm.h”, etc.).

    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
    操作
    -0.07
     holland
    -0.07
     lun
    -0.07
    ormal
    -0.07
     lag
    -0.06
    证
    -0.06
     akce
    -0.06
     Flesh
    -0.06
     Lua
    -0.06
     blood
    -0.06
    POSITIVE LOGITS
    invoke
    0.06
    .Slf
    0.06
    .ConnectionStrings
    0.06
     Làm
    0.06
     DataAccess
    0.06
    .ISupportInitialize
    0.06
    placed
    0.06
    anges
    0.06
     touchscreen
    0.06
     itching
    0.05
    Activations Density 0.004%

    No Known Activations