Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 43777
    Prev
    Next
    INDEX
    Explanations

    U-boats

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of submarines—especially German U-boats and related submarine-warfare terms.

    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
    foundland
    -0.06
    akistan
    -0.06
     Graf
    -0.06
     Safe
    -0.06
    Stride
    -0.06
     pracovní
    -0.06
     shady
    -0.06
     TResult
    -0.06
    ';
    ↵
    -0.06
    _buy
    -0.06
    POSITIVE LOGITS
     зда
    0.06
    otional
    0.06
    �
    0.06
     формы
    0.06
     uploaded
    0.06
    avian
    0.06
     џ
    0.06
    错
    0.06
     تصو
    0.06
     لم
    0.06
    Activations Density 0.003%

    No Known Activations