© 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. 13818
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron specifically flags the “In” token in the word “Invention,” i.e. the patent‐style heading “Field of the Invention.”

    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
    Ping
    -0.07
     Lok
    -0.06
     пл
    -0.06
    olu
    -0.06
     provoz
    -0.06
     počíta
    -0.06
     CrossRef
    -0.06
    ディース
    -0.06
    devil
    -0.06
    esen
    -0.06
    POSITIVE LOGITS
    database
    0.06
    _UINT
    0.06
    txn
    0.06
     referring
    0.06
    射
    0.06
     Hungary
    0.06
     accommod
    0.06
     humiliating
    0.06
     congratulate
    0.06
    "?↵↵
    0.06
    Activations Density 0.000%

    No Known Activations