© 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. 61093
    Prev
    Next
    INDEX
    Explanations

    numerical data and quantifiable parameters

    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
    phem
    -0.07
    illi
    -0.07
    otron
    -0.07
    osl
    -0.07
    uan
    -0.07
    .EntityManager
    -0.06
    ong
    -0.06
    loff
    -0.06
    uet
    -0.06
    alan
    -0.06
    POSITIVE LOGITS
     minimum
    0.08
     single
    0.08
    γι
    0.07
     Single
    0.07
     Minimum
    0.07
     SINGLE
    0.07
    æ±Ĺ
    0.07
    /single
    0.07
     nerve
    0.06
     bell
    0.06
    Activations Density 0.112%

    No Known Activations