© 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. 54838
    Prev
    Next
    INDEX
    Explanations

    steps and instructions related to cooking processes

    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
     sublist
    -0.06
     circulating
    -0.06
    áº
    -0.06
    pek
    -0.06
    rc
    -0.05
     lean
    -0.05
     added
    -0.05
    appro
    -0.05
    ille
    -0.05
     addition
    -0.05
    POSITIVE LOGITS
    orelease
    0.08
    erç
    0.08
    SupportedContent
    0.07
    ToDevice
    0.07
    urar
    0.07
    lej
    0.07
    erin
    0.07
    _tC
    0.07
    pus
    0.07
    odos
    0.07
    Activations Density 0.025%

    No Known Activations