© 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. 9314
    Prev
    Next
    INDEX
    Explanations

    quantities or measurement

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of quantitative technical metrics or performance parameters.

    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
     a
    -0.14
     A
    -0.11
     an
    -0.11
    A
    -0.08
     một
    -0.08
     einen
    -0.07
    .A
    -0.07
     A
    -0.07
    An
    -0.07
     einem
    -0.07
    POSITIVE LOGITS
    enant
    0.07
    getService
    0.07
    IRT
    0.07
    .topic
    0.07
    DELAY
    0.06
    -Line
    0.06
     значення
    0.06
     olmadı
    0.06
     beled
    0.06
    MySQL
    0.06
    Activations Density 0.122%

    No Known Activations