© 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. 86343
    Prev
    Next
    INDEX
    Explanations

    references to food preservation methods and 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
    ãĤŃãĥ¥
    -0.08
    ábado
    -0.08
     sÃłng
    -0.08
    unken
    -0.07
    aeda
    -0.07
    ANCED
    -0.07
     printk
    -0.07
    WithPath
    -0.07
    esine
    -0.07
    licable
    -0.07
    POSITIVE LOGITS
     if
    0.10
     when
    0.07
     for
    0.06
     latter
    0.06
     in
    0.06
     же
    0.06
     actually
    0.06
     since
    0.06
     really
    0.06
     soon
    0.06
    Activations Density 0.038%

    No Known Activations