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. 125322
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric patterns in regular expressions—specifically digit ranges (like `[0-9]`), numeric quantifiers (e.g. `{12}`), and related tokens.

    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
     zřejmě
    -0.08
     yapıldı
    -0.07
             
    -0.07
     salaries
    -0.06
     F
    -0.06
     afternoon
    -0.06
    _heading
    -0.06
    .getDeclared
    -0.06
          
    -0.06
     exposure
    -0.06
    POSITIVE LOGITS
     Прав
    0.08
     öner
    0.07
    -how
    0.07
     tailor
    0.07
    “你
    0.06
    -n
    0.06
     Deutsch
    0.06
     Investments
    0.06
     asoci
    0.06
     Initialise
    0.06
    Activations Density 0.001%

    No Known Activations