© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88935
    Prev
    Next
    INDEX
    Explanations

    desk

    np_max-act · gemini-2.0-flash

    This neuron specifically detects occurrences of the substring “desk,” activating on the token “desk” (and desk-containing variants).

    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
     آب
    -0.08
     Wheat
    -0.07
    OR
    -0.07
    IES
    -0.07
     شیمی
    -0.07
     vlád
    -0.07
    .ObjectModel
    -0.07
     проход
    -0.06
    340
    -0.06
    性的
    -0.06
    POSITIVE LOGITS
     desk
    0.14
     Desk
    0.11
     desks
    0.11
    desk
    0.10
    Desk
    0.10
    kv
    0.08
     Autodesk
    0.08
    esc
    0.07
     tables
    0.07
    esk
    0.07
    Activations Density 0.002%

    No Known Activations