© 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. 126743
    Prev
    Next
    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash

    This neuron activates on Python “NameError” messages indicating an undefined variable or module name.

    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
     Laden
    -0.06
    meldung
    -0.06
    ública
    -0.06
    だよ
    -0.06
    )];↵
    -0.06
    QUE
    -0.06
    _employee
    -0.06
    Pts
    -0.06
     Jenna
    -0.06
     rented
    -0.06
    POSITIVE LOGITS
     discovering
    0.07
    .rdf
    0.07
     термін
    0.07
     *\
    0.07
     instincts
    0.06
    .KEY
    0.06
     handlers
    0.06
    φο
    0.06
     exercising
    0.06
     سی
    0.06
    Activations Density 0.003%

    No Known Activations