© 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. 18183
    Prev
    Next
    INDEX
    Explanations

    references to tax-related timeframes and documentation

    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
    олож
    -0.07
     ↵↵
    -0.07
    icus
    -0.07
    оÑĢаз
    -0.07
    achuset
    -0.07
    Äĥn
    -0.07
    aeda
    -0.06
     alternatives
    -0.06
    ÙĬØ«
    -0.06
    .times
    -0.06
    POSITIVE LOGITS
    201
    0.08
    eck
    0.07
     NA
    0.06
    -placeholder
    0.06
     data
    0.06
    shm
    0.06
    564
    0.06
     calendar
    0.06
    Vintage
    0.06
    Cover
    0.06
    Activations Density 0.029%

    No Known Activations