© 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. 7862
    Prev
    Next
    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash

    The neuron fires on cryptographic key‐generation parameters—specifically the “rsa:2048” (and related numeric) options in code.

    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
     pilots
    -0.06
     ceilings
    -0.06
     carcin
    -0.06
     conversion
    -0.06
    ाब
    -0.06
     adverse
    -0.06
    네요
    -0.06
     timings
    -0.06
     реги
    -0.06
    ित
    -0.06
    POSITIVE LOGITS
     velký
    0.06
     strtol
    0.06
     gọi
    0.06
     Business
    0.06
    getResource
    0.06
    bread
    0.06
    <|end_header_id|>
    0.06
     requestData
    0.06
    衡
    0.06
     resolutions
    0.06
    Activations Density 0.003%

    No Known Activations