© 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. 110132
    Prev
    Next
    INDEX
    Explanations

    locations/names

    np_max-act · gemini-2.0-flash

    This neuron detects erotic or sexual identity language, such as terms like “horny” and “gay.”

    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
     Crescent
    -0.07
     dispensaries
    -0.07
    缩
    -0.07
     Bow
    -0.07
     copyrights
    -0.06
     کر
    -0.06
     biod
    -0.06
    首
    -0.06
    Bow
    -0.06
    ray
    -0.06
    POSITIVE LOGITS
     lidé
    0.07
     Legend
    0.06
    <article
    0.06
    '.↵↵
    0.06
     навч
    0.06
    '})↵
    0.06
    �ng
    0.06
    ━━━━━━━━━━━━━━━━
    0.06
    plementation
    0.06
    imilar
    0.06
    Activations Density 0.103%

    No Known Activations