Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 55727
    Prev
    Next
    INDEX
    Explanations

    Plurality

    np_max-act · gemini-2.0-flash

    the neuron is detecting the appearance of the term “voltage” (especially in its plural form “voltages”).

    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
    arker
    -0.06
     presence
    -0.06
     IX
    -0.06
     robotics
    -0.06
    _st
    -0.06
    宫
    -0.06
     decomposition
    -0.06
     �
    -0.06
     Mush
    -0.06
     opcion
    -0.06
    POSITIVE LOGITS
     events
    0.07
    فن
    0.06
    Minutes
    0.06
    ISE
    0.06
    İSİ
    0.06
    925
    0.06
    پی
    0.06
    .Attributes
    0.06
    aklı
    0.06
     msec
    0.06
    Activations Density 0.208%

    No Known Activations