© 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. 6885
    Prev
    Next
    INDEX
    Explanations

    Military ranks

    np_max-act · gemini-2.0-flash

    The neuron detects military rank titles (e.g. Colonel, Major, Lieutenant General, Brigadier, etc.).

    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
    liced
    -0.07
    Book
    -0.07
    努
    -0.07
    ливості
    -0.07
     Opport
    -0.06
     mis
    -0.06
    itlement
    -0.06
    hard
    -0.06
    ується
    -0.06
    adium
    -0.06
    POSITIVE LOGITS
    ản
    0.07
    .getElements
    0.06
    crets
    0.06
     analyze
    0.06
    (Settings
    0.06
     '--
    0.06
    网络
    0.06
     exponent
    0.06
    '+↵
    0.06
     Ре
    0.06
    Activations Density 0.003%

    No Known Activations