© 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. 690
    Prev
    Next
    INDEX
    Explanations

    legal and people

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of individual people or personal entities (i.e. references to persons).

    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
     improvised
    -0.07
    ικές
    -0.06
     usuário
    -0.06
     druh
    -0.06
    ثمان
    -0.06
     комнат
    -0.06
    论文
    -0.06
     คำ
    -0.06
    装置
    -0.06
    (icon
    -0.06
    POSITIVE LOGITS
    /%
    0.06
     $('#
    0.06
     getState
    0.06
    “That
    0.06
    ει
    0.06
    HAL
    0.06
    ธน
    0.06
    widget
    0.06
     heightened
    0.06
     stabilized
    0.06
    Activations Density 0.084%

    No Known Activations