© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126816
    Prev
    Next
    INDEX
    Explanations

    Arch

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of the Linux distribution “Arch Linux.”

    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
    deck
    -0.07
     Marg
    -0.07
     Bark
    -0.06
    Eng
    -0.06
    izations
    -0.06
     Beg
    -0.06
     VA
    -0.06
    ashes
    -0.06
    маз
    -0.06
     Siber
    -0.06
    POSITIVE LOGITS
     recursively
    0.06
    (KeyCode
    0.06
    escort
    0.06
     khuyến
    0.06
    くん
    0.06
     oluş
    0.06
     dein
    0.06
    高校
    0.06
    Assoc
    0.06
    _gp
    0.06
    Activations Density 0.002%

    No Known Activations