© 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. 41623
    Prev
    Next
    INDEX
    Explanations

    Hon

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect honorifics and aristocratic titles (e.g. Lord, Hon., Lady, Baron, Earl) that precede personal names.

    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
     SSE
    -0.07
    葉
    -0.07
    -find
    -0.07
    분
    -0.07
     Sal
    -0.07
    Blood
    -0.07
    AF
    -0.07
    .Comp
    -0.06
    fraction
    -0.06
     substitutes
    -0.06
    POSITIVE LOGITS
    lığ
    0.07
    ENDED
    0.07
    nda
    0.06
     endless
    0.06
     무엇
    0.06
     případ
    0.06
    xmlns
    0.06
    lasting
    0.06
    @ResponseBody
    0.06
    lası
    0.06
    Activations Density 0.010%

    No Known Activations