© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109705
    Prev
    Next
    INDEX
    Explanations

    Ensure

    np_max-act · gemini-2.0-flash

    The neuron fires on interrogative question phrases (e.g. “What…?”, “How many…?”, “Which…?”) indicating it’s detecting question stems.

    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
    axe
    -0.07
     seat
    -0.07
    Put
    -0.07
     veterinary
    -0.06
     Consort
    -0.06
     guitars
    -0.06
    武器
    -0.06
    vant
    -0.06
     manžel
    -0.06
    族自治
    -0.06
    POSITIVE LOGITS
     biz
    0.06
     espaço
    0.06
     halfway
    0.06
    Gam
    0.06
    gota
    0.06
    ibilidad
    0.06
     wishes
    0.06
    	setTimeout
    0.06
     depended
    0.06
    =\""
    0.06
    Activations Density 0.015%

    No Known Activations