© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128680
    Prev
    Next
    INDEX
    Explanations

    personal finance

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of personal or self-funded money—dollar amounts and terms indicating using one’s own funds.

    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
    (remove
    -0.07
     원
    -0.07
    tags
    -0.06
    냥
    -0.06
     Bei
    -0.06
     وع
    -0.06
    scss
    -0.06
    _generation
    -0.06
    '>↵
    -0.06
     Get
    -0.06
    POSITIVE LOGITS
    .How
    0.06
     dissolve
    0.06
     parental
    0.06
    Highlights
    0.06
     proving
    0.06
     прави
    0.06
     gouver
    0.06
    prim
    0.06
     CBS
    0.06
    腹
    0.06
    Activations Density 0.005%

    No Known Activations