© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129870
    Prev
    Next
    INDEX
    Explanations

    This neuron detects words and phrases that emphasize graphic, highly detailed sexual content (e.g., “graphic,” “detailed,” “specific,” “descriptions”).

    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
    еле
    -0.07
     DataSet
    -0.07
    .Player
    -0.07
    .mkdirs
    -0.06
     objetos
    -0.06
     labeling
    -0.06
    flash
    -0.06
     프로
    -0.06
    家庭
    -0.06
     Premi
    -0.06
    POSITIVE LOGITS
    /free
    0.06
     unrealistic
    0.06
    orgh
    0.06
    inea
    0.06
     прямо
    0.06
    는지
    0.06
    META
    0.06
     rok
    0.06
    -common
    0.06
     назва
    0.06
    Activations Density 0.020%

    No Known Activations