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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8607
    Prev
    Next
    INDEX
    Explanations

    cum

    np_max-act · gemini-2.0-flash

    The neuron detects explicit references to sexual climax or ejaculation (e.g., “cum,” “coming”).

    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
    _ste
    -0.07
    obile
    -0.07
     Energ
    -0.06
     ایت
    -0.06
    asje
    -0.06
     Mazda
    -0.06
    .Ge
    -0.06
    lectric
    -0.06
    ária
    -0.06
    .Minimum
    -0.06
    POSITIVE LOGITS
     compensated
    0.08
     cum
    0.07
     cumulative
    0.07
    derived
    0.07
    _cum
    0.07
    UM
    0.07
    cum
    0.07
     Durch
    0.07
    um
    0.06
     Cummings
    0.06
    Activations Density 0.003%

    No Known Activations