© 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. 110086
    Prev
    Next
    INDEX
    Explanations

    job titles

    np_max-act · gemini-2.0-flash

    The neuron activates on words denoting a person’s formal role, title, or official position.

    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
    ost
    -0.06
    .writeString
    -0.06
     František
    -0.06
    postId
    -0.06
     deepen
    -0.06
     qi
    -0.06
     पढ़
    -0.05
     mejorar
    -0.05
    レ
    -0.05
     '../../../../../
    -0.05
    POSITIVE LOGITS
    ΗΝ
    0.07
    انی
    0.07
    <style
    0.07
     <%
    0.07
    .inst
    0.07
    }';↵
    0.07
    cker
    0.06
     misunderstood
    0.06
     Substitute
    0.06
     Zimbabwe
    0.06
    Activations Density 0.028%

    No Known Activations