© 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. 91644
    Prev
    Next
    INDEX
    Explanations

    ants

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect the German word “Pflanzen” (and its subword pieces) whenever it appears in the text.

    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
     breakpoint
    -0.07
    .ba
    -0.07
     Harding
    -0.06
     dzi
    -0.06
     //{
↵
    -0.06
     {
↵
↵
↵
    -0.06
     bet
    -0.06
    事故
    -0.06
    archy
    -0.06
    Eigen
    -0.06
    POSITIVE LOGITS
     UNITED
    0.08
     plants
    0.07
     گیاه
    0.07
     planned
    0.07
     teor
    0.06
     tackle
    0.06
     flora
    0.06
     rooted
    0.06
     United
    0.06
     minist
    0.06
    Activations Density 0.022%

    No Known Activations