© 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. 6909
    Prev
    Next
    INDEX
    Explanations

    Determining goals or needs

    np_max-act · gemini-2.0-flash

    This neuron activates on the imperative‐style step headings in how-to instructions (e.g. “Define the scope of your chatbot: Determine what kind of information you want…”), highlighting the verbs and punctuation that mark each procedural step.

    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
     Ending
    -0.06
    PREFIX
    -0.06
    rive
    -0.06
    怎么
    -0.06
    was
    -0.06
    etary
    -0.06
    여
    -0.06
    бов
    -0.06
    Ping
    -0.06
     lovely
    -0.06
    POSITIVE LOGITS
    "';
    0.07
     Sexe
    0.06
     Şampiyon
    0.06
     vida
    0.06
     maior
    0.06
     miglior
    0.06
    ตำบล
    0.06
    EPHIR
    0.06
     проф
    0.06
     Login
    0.06
    Activations Density 0.065%

    No Known Activations