© 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. 85809
    Prev
    Next
    INDEX
    Explanations

    smell

    np_max-act · gemini-2.0-flash

    The neuron fires on sensory‐description terms in wine tasting notes (e.g. color, aromas, flavors, nose, palate, finish, body, tannins, acidity).

    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
     く
    -0.07
     chair
    -0.07
    ;(
    -0.06
    柏
    -0.06
     अच
    -0.06
    랍
    -0.06
     선택
    -0.06
    Pixmap
    -0.06
     volunt
    -0.06
     tahmin
    -0.06
    POSITIVE LOGITS
     shower
    0.06
    šit
    0.06
    )$_
    0.06
     ECS
    0.06
     Difference
    0.06
    τή
    0.06
    ổi
    0.05
    ower
    0.05
     Supplementary
    0.05
    /');↵
    0.05
    Activations Density 0.005%

    No Known Activations