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. 126661
    Prev
    Next
    INDEX
    Explanations

    crime and people

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of a “resident” or similar occupant (e.g. “wealthy resident,” “resident’s family,” etc.).

    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
     �
    -0.08
    ビ
    -0.06
    ANCELED
    -0.06
    smart
    -0.06
     ม
    -0.06
    .peer
    -0.06
     rebut
    -0.06
    游
    -0.06
    259
    -0.06
     AQ
    -0.06
    POSITIVE LOGITS
     sánh
    0.06
     Inject
    0.06
    stackoverflow
    0.06
    ="#"><
    0.06
     juste
    0.06
     sigh
    0.06
     hlav
    0.06
    straight
    0.06
     accomplish
    0.06
     excitement
    0.06
    Activations Density 0.049%

    No Known Activations