© 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. 55542
    Prev
    Next
    INDEX
    Explanations

    personality disorders

    np_max-act · gemini-2.0-flash

    The neuron fires on words expressing a person’s strong need for attention, care, or recognition (e.g. “importance,” “need,” “admiration,” “be,” “care”).

    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
    Robin
    -0.07
     Marian
    -0.07
    batim
    -0.06
     ایت
    -0.06
    ทำงาน
    -0.06
    札
    -0.06
     Kur
    -0.06
     yt
    -0.06
    ADDRESS
    -0.06
     快
    -0.06
    POSITIVE LOGITS
    )<
    0.07
    (man
    0.06
    /↵↵↵
    0.06
     вост
    0.06
     annoyance
    0.06
    Adapter
    0.06
     розп
    0.06
     yi
    0.06
    (subject
    0.06
    Edward
    0.06
    Activations Density 0.045%

    No Known Activations