Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43926
    Prev
    Next
    INDEX
    Explanations

    qi

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric measurement tokens—especially fragments of decimal numbers and other numeric data.

    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
     literally
    -0.07
     Whatsapp
    -0.07
     assortment
    -0.07
     indications
    -0.07
     london
    -0.07
     möchten
    -0.06
    =g
    -0.06
    _Cancel
    -0.06
    	change
    -0.06
     chicago
    -0.06
    POSITIVE LOGITS
     وحدة
    0.07
    oriented
    0.06
    Export
    0.06
    inium
    0.06
     ruthless
    0.06
    ське
    0.06
    oned
    0.06
    Soph
    0.06
     qualidade
    0.06
    _glob
    0.06
    Activations Density 0.263%

    No Known Activations