© 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. 13136
    Prev
    Next
    INDEX
    Explanations

    system administration

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of specific software or protocol names (like SSH, Git, Python) in configuration or how-to instructions.

    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
     coll
    -0.06
    /by
    -0.06
    >`↵
    -0.06
    ';↵↵↵
    -0.06
    /↵↵↵
    -0.06
    _
    ↵
    ↵
    -0.06
    rior
    -0.06
    >manual
    -0.06
    *=*=
    -0.06
     вд
    -0.06
    POSITIVE LOGITS
    建
    0.06
     settlers
    0.06
     �
    0.06
    DW
    0.06
     vốn
    0.06
    اطق
    0.06
    charAt
    0.06
     retour
    0.06
     ΠΑΝ
    0.06
    Impact
    0.06
    Activations Density 0.013%

    No Known Activations