© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12449
    Prev
    Next
    INDEX
    Explanations

    year

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “year-round” (and close variants like “year around”), i.e. expressions indicating something is available throughout the year.

    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
     Nová
    -0.06
    (cx
    -0.06
    итив
    -0.06
     Merkel
    -0.06
    ncmp
    -0.06
     Epic
    -0.06
    Iter
    -0.06
     blasted
    -0.06
    	trans
    -0.06
     clas
    -0.06
    POSITIVE LOGITS
     spinner
    0.07
    _plot
    0.06
     xúc
    0.06
     texture
    0.06
    -long
    0.06
     threaded
    0.06
     released
    0.06
    inya
    0.06
     ],↵
    0.06
    ازد
    0.06
    Activations Density 0.004%

    No Known Activations