© 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. 29312
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms followed by relevant terms or categories

    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
    jac
    -0.06
     nearly
    -0.06
    .Compose
    -0.06
     Nearly
    -0.06
     Tales
    -0.06
     Tale
    -0.06
    inary
    -0.05
    ãĤŃãĥ¥
    -0.05
    Attach
    -0.05
    FRING
    -0.05
    POSITIVE LOGITS
    ables
    0.07
    ÛĮرÙĩ
    0.07
    ÛĮرÛĮ
    0.07
    .sdk
    0.07
    ered
    0.07
    emble
    0.07
    ogany
    0.07
    ÙĪرد
    0.07
    yclopedia
    0.07
    lopedia
    0.07
    Activations Density 0.026%

    No Known Activations