© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109796
    Prev
    Next
    INDEX
    Explanations

    Matrix

    np_max-act · gemini-2.0-flash

    the neuron responds strongly to mentions of the word “Matrix.”

    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
    とい
    -0.07
    322
    -0.07
    comed
    -0.06
    beit
    -0.06
    جمة
    -0.06
     Border
    -0.06
     деньги
    -0.06
    Border
    -0.06
    [..
    -0.06
     foremost
    -0.06
    POSITIVE LOGITS
     auditing
    0.06
    _Matrix
    0.06
     usar
    0.06
    刘
    0.06
     financially
    0.06
     κο
    0.06
     essence
    0.06
    -commit
    0.06
     겨
    0.06
     RDF
    0.06
    Activations Density 0.002%

    No Known Activations