Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55248
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on words referring to slavery—especially sexual slavery—and related roles (e.g. slave, sex slave, owner, concubine).

    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
    adık
    -0.06
     pár
    -0.06
     Cardiff
    -0.06
    mekte
    -0.06
    _sa
    -0.06
     MAC
    -0.06
    923
    -0.06
    atab
    -0.06
     Ein
    -0.06
    ))*
    -0.05
    POSITIVE LOGITS
     uuid
    0.07
    жень
    0.07
     pcl
    0.07
     lombok
    0.06
    .Tags
    0.06
    notes
    0.06
     Hlav
    0.06
    .Produ
    0.06
     kayn
    0.06
     سرو
    0.06
    Activations Density 0.045%

    No Known Activations