© 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. 5406
    Prev
    Next
    INDEX
    Explanations

    references to locally sourced and fresh food ingredients

    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
    indr
    -0.08
    iž
    -0.07
    æ´ĭ
    -0.07
    énom
    -0.07
    _pb
    -0.07
    atee
    -0.07
     !***
    -0.07
     archit
    -0.07
    íݸ
    -0.07
    ãİ¡
    -0.07
    POSITIVE LOGITS
     local
    0.11
     locally
    0.10
     Local
    0.09
    /local
    0.09
    .local
    0.08
    local
    0.08
     LOCAL
    0.08
    Local
    0.08
    (local
    0.08
     farm
    0.08
    Activations Density 0.021%

    No Known Activations