© 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. 696
    Prev
    Next
    INDEX
    Explanations

    application/app

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on words referring to the software “application” or “app” context (e.g., application, app, pages).

    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
     screamed
    -0.07
     trot
    -0.07
    .Head
    -0.06
     wird
    -0.06
     dto
    -0.06
     Kickstarter
    -0.06
    ciler
    -0.06
     ihn
    -0.06
    /time
    -0.06
    allo
    -0.06
    POSITIVE LOGITS
    .Di
    0.07
    (script
    0.07
     Hemp
    0.07
    _TRAN
    0.07
    ');</
    0.07
     Slovenia
    0.07
     App
    0.07
     Blaze
    0.07
    .Namespace
    0.07
     Proposition
    0.06
    Activations Density 0.020%

    No Known Activations