© 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. 15-RESID-POST-AA
    11. 37545
    Prev
    Next
    INDEX
    Explanations

    runtime

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the token "runtime" (mentions of runtime/runtime-related environment).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	vec
    -0.07
     Herc
    -0.07
     jo
    -0.07
     jobject
    -0.07
     JComboBox
    -0.07
    xab
    -0.07
     occ
    -0.07
     dol
    -0.07
     Coc
    -0.07
    _rem
    -0.06
    POSITIVE LOGITS
     runtime
    0.07
     Amit
    0.07
    hta
    0.07
    input
    0.07
    UIT
    0.07
    TED
    0.07
     겁
    0.07
    ime
    0.07
    ITS
    0.07
     культуры
    0.07
    Activations Density 0.008%

    No Known Activations