© 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. 12956
    Prev
    Next
    INDEX
    Explanations

    positions of authority

    np_max-act · gemini-2.0-flash

    This neuron activates on words denoting ranks or formal titles (e.g., military or organizational positions).

    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
    الك
    -0.07
    scoped
    -0.06
    Message
    -0.06
    ्रपत
    -0.06
     Advertisement
    -0.06
     süreci
    -0.06
    _BB
    -0.06
    pop
    -0.05
    �
    -0.05
     internet
    -0.05
    POSITIVE LOGITS
    =_('
    0.07
     BMW
    0.07
    환
    0.07
    aven
    0.06
     luxurious
    0.06
    rgctx
    0.06
     carr
    0.06
     "->
    0.06
    (strict
    0.06
     Called
    0.06
    Activations Density 0.021%

    No Known Activations