© 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 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. 38428
    Prev
    Next
    INDEX
    Explanations

    server

    np_max-act · gemini-2.0-flash

    The neuron fires on references to server‐ or service‐related class names and terms (e.g. “Server,” “server,” “HTTPServer,” “RequestHandler,” 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
    开奖
    -0.07
     Ros
    -0.06
     St
    -0.06
     Moist
    -0.06
     Hass
    -0.06
    녀
    -0.06
     oo
    -0.06
    プレ
    -0.06
    єте
    -0.06
     goats
    -0.06
    POSITIVE LOGITS
     нал
    0.07
     signup
    0.07
    hod
    0.07
    owner
    0.07
    archical
    0.06
     afirm
    0.06
    lain
    0.06
     Simpl
    0.06
    designation
    0.06
     لازم
    0.06
    Activations Density 0.002%

    No Known Activations