© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129799
    Prev
    Next
    INDEX
    Explanations

    nudity/sexual content

    np_max-act · gemini-2.0-flash

    The neuron fires on explicit sexual content—especially references to pornographic leaks, private nude photos, and erotic body-part terms.

    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
     congressman
    -0.07
     kol
    -0.06
     deselect
    -0.06
    125
    -0.06
                                                       
    -0.06
    .xls
    -0.06
    .fasterxml
    -0.06
     Ras
    -0.06
    .profile
    -0.06
    .semantic
    -0.06
    POSITIVE LOGITS
    něm
    0.06
     Ezek
    0.06
     Cic
    0.06
    生活
    0.06
    ujte
    0.06
    <>
    0.06
     Česk
    0.06
     आप
    0.06
     поля
    0.06
    жи
    0.06
    Activations Density 0.221%

    No Known Activations