© 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. 85723
    Prev
    Next
    INDEX
    Explanations

    recommendations and rules

    np_max-act · gemini-2.0-flash

    The neuron primarily fires on numerical expressions (quantities, percentages, decimal values) and words signaling guidelines or recommendations (e.g., “recommended,” “limit,” “maximum,” “legal,” “guidelines”).

    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
     emailed
    -0.06
    enton
    -0.06
    利
    -0.06
     bons
    -0.06
     Generating
    -0.06
    .transparent
    -0.06
     clas
    -0.06
    ped
    -0.06
     apa
    -0.06
    .Rest
    -0.06
    POSITIVE LOGITS
    >');↵
    0.08
     BaseController
    0.06
     LAST
    0.06
    __)↵↵
    0.06
     MouseEventArgs
    0.06
     sayısı
    0.06
    ?)↵↵
    0.06
     Dess
    0.06
     HUD
    0.06
     dtype
    0.06
    Activations Density 0.026%

    No Known Activations