© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41220
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron fires on Go client‐library doc lines that describe resource methods (e.g. “Get takes … and returns …”), i.e. it detects those API-method signature comment patterns.

    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
     ridge
    -0.06
    .app
    -0.06
     manipulated
    -0.06
    .navCtrl
    -0.06
     مرک
    -0.06
     addSubview
    -0.06
     injection
    -0.06
    ･･
    -0.06
    ersion
    -0.06
     Comet
    -0.06
    POSITIVE LOGITS
     inşa
    0.07
     Retorna
    0.07
    itas
    0.06
    орож
    0.06
     doses
    0.06
    ])]
    0.06
    semble
    0.06
    <boost
    0.06
    actal
    0.06
    ilig
    0.06
    Activations Density 0.003%

    No Known Activations