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

    Neuronpedia

    Jacobian LensNEW
    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. 38831
    Prev
    Next
    INDEX
    Explanations

    plate

    np_max-act · gemini-2.0-flash

    The neuron activates on technical terms naming lead–acid battery components and related materials (e.g. “battery,” “acid,” “plates”).

    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
    esin
    -0.06
    *****↵↵
    -0.06
    :'#
    -0.06
     ребен
    -0.06
    \Event
    -0.06
     KeyEvent
    -0.06
    Author
    -0.06
    StreamWriter
    -0.06
    айд
    -0.06
    adaptive
    -0.06
    POSITIVE LOGITS
    .scan
    0.07
    'nde
    0.07
    _seek
    0.06
    .enumer
    0.06
    .allow
    0.06
     prompting
    0.06
     flight
    0.06
     patent
    0.06
    	RTCT
    0.06
     SEEK
    0.06
    Activations Density 0.606%

    No Known Activations