© 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. 8939
    Prev
    Next
    INDEX
    Explanations

    categories

    np_max-act · gemini-2.0-flash

    The neuron fires on category lines indicating an institution’s founding year, i.e. the “established in [year]” year tokens.

    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
     homeowners
    -0.07
     Bulldogs
    -0.06
     เก
    -0.06
     healed
    -0.06
     Consultant
    -0.06
     []).
    -0.06
    데
    -0.06
    .tabControl
    -0.06
     titanium
    -0.06
     lord
    -0.06
    POSITIVE LOGITS
     listop
    0.07
     dříve
    0.06
     kabil
    0.06
    truncate
    0.06
    集合
    0.06
     anv
    0.06
     ін
    0.06
     sentinel
    0.06
    σπ
    0.06
     ba
    0.06
    Activations Density 0.003%

    No Known Activations