© 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. 94653
    Prev
    Next
    INDEX
    Explanations

    mentions of lost items and the surrounding circumstances

    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
    isay
    -0.06
     collapsing
    -0.06
    ogi
    -0.06
    ÙĨدا
    -0.06
     barrier
    -0.06
    ippi
    -0.06
    Trader
    -0.05
     pev
    -0.05
     backward
    -0.05
     Musk
    -0.05
    POSITIVE LOGITS
     lost
    0.18
     Lost
    0.17
    Lost
    0.16
    lost
    0.15
     missing
    0.14
    _lost
    0.13
    missing
    0.13
     Missing
    0.12
     misplaced
    0.12
    Missing
    0.12
    Activations Density 0.083%

    No Known Activations