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

    Neuronpedia

    Jacobian LensNEW
    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. 57428
    Prev
    Next
    INDEX
    Explanations

    Lists and commas

    np_max-act · gemini-2.0-flash

    The neuron flags tokens that are part of technical lists or specs—especially alphanumeric model names and numbers (e.g. “PS3,” “2600,” version numbers, platform lists).

    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
     folded
    -0.08
     empath
    -0.06
    温度
    -0.06
    هن
    -0.06
     embr
    -0.06
     tee
    -0.06
    บบ
    -0.06
    뢰
    -0.06
    owered
    -0.06
    jual
    -0.05
    POSITIVE LOGITS
    dıkları
    0.07
    тор
    0.07
    (separator
    0.07
     RelayCommand
    0.07
     NodeList
    0.06
    (ROOT
    0.06
    .listen
    0.06
    _thumbnail
    0.06
    .authentication
    0.06
     *\
    0.06
    Activations Density 0.168%

    No Known Activations