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. 26904
    Prev
    Next
    INDEX
    Explanations

    sexual activity

    np_max-act · gemini-2.0-flash

    The neuron chiefly responds to explicit mentions of orgasm (especially the word “cum”) in sexual contexts.

    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
    o
    -0.07
    edula
    -0.07
     свого
    -0.06
     specialties
    -0.06
     todos
    -0.06
    _Zero
    -0.06
              
    -0.06
     razor
    -0.06
     Cross
    -0.06
     melody
    -0.06
    POSITIVE LOGITS
    Already
    0.07
     내
    0.07
    aines
    0.06
    廷
    0.06
     Regards
    0.06
     elders
    0.06
    -more
    0.06
    §
    0.06
     Meetings
    0.06
    -readable
    0.06
    Activations Density 0.016%

    No Known Activations