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

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95011
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols that may represent technical or coding elements

    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
    alt
    -0.07
    eler
    -0.06
    icker
    -0.06
    qn
    -0.06
    ala
    -0.06
    ign
    -0.06
    inine
    -0.06
    estar
    -0.06
    askan
    -0.06
    finity
    -0.06
    POSITIVE LOGITS
    steller
    0.07
    plier
    0.06
     Tas
    0.06
    odesk
    0.06
    izophren
    0.06
    orderby
    0.06
    /repository
    0.06
     Gros
    0.06
    cum
    0.06
    amik
    0.06
    Activations Density 0.007%

    No Known Activations