© 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
    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. 42582
    Prev
    Next
    INDEX
    Explanations

    The neuron is spotting explicit sexual content—particularly graphic descriptions of sexual acts and violence.

    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
    _DRV
    -0.06
    _pes
    -0.06
     Under
    -0.06
    uem
    -0.06
    xito
    -0.06
    /widget
    -0.06
    _until
    -0.06
     مقر
    -0.06
     phổ
    -0.06
    ư
    -0.06
    POSITIVE LOGITS
     Bell
    0.07
    _MOBILE
    0.07
     Founder
    0.06
    .childNodes
    0.06
    received
    0.06
     founder
    0.06
     pretty
    0.06
    _UPLOAD
    0.06
    илась
    0.06
     مرگ
    0.06
    Activations Density 0.042%

    No Known Activations