© 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. 91697
    Prev
    Next
    INDEX
    Explanations

    Maria

    np_max-act · gemini-2.0-flash

    The neuron fires on the names of specific software products—especially database engines (e.g. “MariaDB”) and Linux distributions (e.g. “CentOS,” “Rocky Linux”).

    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
    @endif
    -0.07
    Jesus
    -0.06
    /write
    -0.06
    /////
    -0.06
    以前
    -0.06
    ////
    -0.06
     Sunny
    -0.06
     saints
    -0.06
    Size
    -0.06
     Evropy
    -0.06
    POSITIVE LOGITS
     favors
    0.07
    âb
    0.07
     alterations
    0.06
    _dw
    0.06
     Mov
    0.06
    adies
    0.06
    alış
    0.06
     collabor
    0.06
    обходим
    0.06
    unuz
    0.06
    Activations Density 0.009%

    No Known Activations