© 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 EvalsExportsinterp-engineNEWAPI 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. 123992
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in context

    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
    ÅŁa
    -0.07
    .Pixel
    -0.06
     Dating
    -0.06
     dating
    -0.06
    196
    -0.06
    195
    -0.06
    uo
    -0.06
     ç¸
    -0.06
    olin
    -0.06
    porte
    -0.06
    POSITIVE LOGITS
     ÙħÛĮÙĦادÛĮ
    0.08
    ayne
    0.07
    amd
    0.07
    otos
    0.07
    treeview
    0.06
    opy
    0.06
    essages
    0.06
    uge
    0.06
    ái
    0.06
    -present
    0.06
    Activations Density 0.062%

    No Known Activations