© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6870
    Prev
    Next
    INDEX
    Explanations

    K-12

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific educational grade or school levels (e.g., “K-12,” “grammar,” “secondary,” “college,” “PK”).

    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
    _ar
    -0.06
     bibli
    -0.06
    unread
    -0.06
    -speaking
    -0.06
    WA
    -0.06
    _space
    -0.06
     sug
    -0.06
    _Handle
    -0.06
     mutual
    -0.06
     sexdate
    -0.06
    POSITIVE LOGITS
     výro
    0.07
     індив
    0.07
     Medieval
    0.07
    !');↵
    0.06
     coverage
    0.06
    imonials
    0.06
    nota
    0.06
    [index
    0.06
     임
    0.06
    ोषण
    0.06
    Activations Density 0.013%

    No Known Activations