© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30692
    Prev
    Next
    INDEX
    Explanations

    Wikipedia articles

    np_max-act · gemini-2.0-flash

    The neuron detects named technical notation systems or terminology (e.g. “Hungarian notation,” “Drakon‐charts,” “chemical formulas,” etc.).

    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
    %C
    -0.07
    ##
    -0.07
    ژی
    -0.07
    ###
    -0.07
    وبی
    -0.07
    अ
    -0.07
    restart
    -0.06
    ("../
    -0.06
    Vote
    -0.06
    ="/"
    -0.06
    POSITIVE LOGITS
    辞
    0.06
     Lebanese
    0.06
     QLabel
    0.06
     std
    0.06
    _EMP
    0.05
    availability
    0.05
     pandemic
    0.05
     Convenient
    0.05
     relics
    0.05
    	boost
    0.05
    Activations Density 0.038%

    No Known Activations