© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 56027
    Prev
    Next
    INDEX
    Explanations

    programming-related commands and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wheeler
    -0.07
    sik
    -0.06
    ستاÙĨ
    -0.06
    tual
    -0.06
    btc
    -0.06
    ãģ¤ãģij
    -0.06
    ondon
    -0.06
    eyen
    -0.06
    pest
    -0.06
     ì°¨
    -0.06
    POSITIVE LOGITS
    ilk
    0.09
     withObject
    0.07
    ilty
    0.06
    wil
    0.06
    -ready
    0.06
    ovy
    0.06
    partials
    0.06
    olec
    0.06
    ,{"
    0.06
    енÑĮÑİ
    0.06
    Activations Density 0.030%

    No Known Activations