© 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. 30415
    Prev
    Next
    INDEX
    Explanations

    services to same-sex couples

    np_max-act · gemini-2.0-flash

    This neuron detects formal legal or legislative language, especially provisions and terminology in statutes or referendum text.

    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
    식
    -0.07
    .board
    -0.07
     world
    -0.06
    Empresa
    -0.06
     novels
    -0.06
     lobbyists
    -0.06
    ANY
    -0.06
     гер
    -0.06
     downgrade
    -0.06
     alter
    -0.06
    POSITIVE LOGITS
    {};↵
    0.07
    [L
    0.06
     accessor
    0.06
    {Name
    0.06
     Explos
    0.06
    >>,
    0.06
    malloc
    0.06
     Patriot
    0.06
     pově
    0.06
    τά
    0.06
    Activations Density 0.024%

    No Known Activations