© 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
    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. 92204
    Prev
    Next
    INDEX
    Explanations

    Acronyms and initialisms

    np_max-act · gemini-2.0-flash

    This neuron detects the NSFW label—instances of “NSFW” or its expansion “not safe for work.”

    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
     ста
    -0.07
    ekte
    -0.06
    imity
    -0.06
     hình
    -0.06
    ене
    -0.06
     VE
    -0.06
    <Movie
    -0.06
    .bb
    -0.06
    เวลา
    -0.06
     форме
    -0.06
    POSITIVE LOGITS
     chief
    0.07
     critiques
    0.06
     />↵
    0.06
    _workflow
    0.06
    .parts
    0.06
     ironic
    0.06
    >").
    0.06
    Plot
    0.06
     '"';↵
    0.06
    .read
    0.06
    Activations Density 0.019%

    No Known Activations