© 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 EvalsExportsinterp-engineNEWAPI 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. 57875
    Prev
    Next
    INDEX
    Explanations

    computers/machines

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to mentions of “32-bit” or “64-bit” environments (e.g. “64 bit machine,” “32 bit application”).

    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
    	Size
    -0.08
     почему
    -0.07
    мовір
    -0.07
    isex
    -0.07
    486
    -0.07
    _type
    -0.07
    	Vector
    -0.06
    (userId
    -0.06
    純
    -0.06
    Training
    -0.06
    POSITIVE LOGITS
     hometown
    0.06
     distract
    0.06
    fh
    0.06
     rightfully
    0.06
    lf
    0.06
     rsp
    0.06
    FT
    0.06
     hydraulic
    0.06
    -inch
    0.06
     mortgages
    0.05
    Activations Density 0.053%

    No Known Activations