© 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. 41450
    Prev
    Next
    INDEX
    Explanations

    compound terms denoting durations of time or length

    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
    reau
    -0.07
    ESP
    -0.07
     lifelong
    -0.06
    267
    -0.06
    αι
    -0.06
     Brother
    -0.06
    TOTYPE
    -0.06
    éĿĪ
    -0.06
    TypeEnum
    -0.06
    297
    -0.06
    POSITIVE LOGITS
    ende
    0.08
    utes
    0.07
    iche
    0.07
    uen
    0.07
    emouth
    0.07
    /month
    0.07
     effort
    0.07
    uet
    0.07
    ournal
    0.07
    isode
    0.07
    Activations Density 0.012%

    No Known Activations