© 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. 6777
    Prev
    Next
    INDEX
    Explanations

    steam

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of steam or humidifier inhalation and related nasal rinsing (e.g. “steam,” “humidifier,” “saline,” “inhaling,” “nasal”).

    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
     Pyongyang
    -0.07
    Cur
    -0.07
    <View
    -0.06
     파
    -0.06
    Ế
    -0.06
    .imp
    -0.06
     GetComponent
    -0.06
    Ă
    -0.06
     Foster
    -0.06
     centr
    -0.06
    POSITIVE LOGITS
     //!<
    0.07
     garments
    0.07
    POP
    0.07
     noises
    0.06
     Necklace
    0.06
    い
    0.06
    -government
    0.06
    希
    0.06
    {Name
    0.06
     fecha
    0.06
    Activations Density 0.005%

    No Known Activations