© 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. 68690
    Prev
    Next
    INDEX
    Explanations

    network communication protocols

    np_max-act · gemini-2.0-flash

    The neuron detects technical protocol- or signaling-action terms (e.g. association, exchange, encryption, control) in wireless communication descriptions.

    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
     kỹ
    -0.07
    KeyValue
    -0.07
     Parkinson
    -0.07
    _USE
    -0.07
    _profiles
    -0.06
    .tv
    -0.06
    xAB
    -0.06
     наблюд
    -0.06
    	wx
    -0.06
    Release
    -0.06
    POSITIVE LOGITS
    -moving
    0.07
    getic
    0.06
     lucky
    0.06
    abolic
    0.06
     ¡
    0.06
    soever
    0.06
     lawsuits
    0.06
     seventy
    0.06
     eagle
    0.06
     agricult
    0.06
    Activations Density 0.023%

    No Known Activations