© 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. 84333
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical or coding values in technical contexts

    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
    ÃĬ
    -0.07
     pÅĻÃŃpadnÄĽ
    -0.07
    ÄIJT
    -0.07
    Disallow
    -0.07
    676
    -0.07
    sed
    -0.07
    .setRotation
    -0.07
    udeau
    -0.07
    avis
    -0.07
    çħ
    -0.07
    POSITIVE LOGITS
    yers
    0.06
    sson
    0.06
     Vance
    0.05
    spb
    0.05
    ftware
    0.05
    ãĢħ
    0.05
    amp
    0.05
    itsu
    0.05
    uploader
    0.05
    apons
    0.05
    Activations Density 0.841%

    No Known Activations