© 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 EvalsExportsAPI 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. 106209
    Prev
    Next
    INDEX
    Explanations

    references to food menus and dining options

    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
    bling
    -0.07
    éij
    -0.07
    /tiny
    -0.06
    hod
    -0.06
    .googleapis
    -0.06
    vine
    -0.06
    intosh
    -0.06
     histo
    -0.06
    zw
    -0.06
    ÅĽnie
    -0.06
    POSITIVE LOGITS
     dÄ±ÅŁÄ±
    0.09
    inaire
    0.08
     vitae
    0.07
    reuse
    0.07
    items
    0.07
     items
    0.07
    pread
    0.07
    emme
    0.07
    ação
    0.06
    ouve
    0.06
    Activations Density 0.005%

    No Known Activations