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. 12819
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on words describing physical sexual stimulation or arousal sensations.

    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
    ربه
    -0.07
    arro
    -0.07
    feed
    -0.06
     meds
    -0.06
    "):
    ↵
    -0.06
    跳
    -0.06
    ancing
    -0.06
    urus
    -0.06
      
    -0.06
    ######↵
    -0.06
    POSITIVE LOGITS
    _imgs
    0.06
     Cleaner
    0.06
     revered
    0.06
    Falsy
    0.06
    pol
    0.06
     obchodní
    0.06
    /bash
    0.06
    arsimp
    0.06
    _medium
    0.06
     IPPROTO
    0.06
    Activations Density 0.803%

    No Known Activations