© 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. 30818
    Prev
    Next
    INDEX
    Explanations

    references to products available for purchase, particularly related to machinery and home goods

    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
    ctor
    -0.08
    pires
    -0.06
    ILA
    -0.06
    rene
    -0.06
    worm
    -0.06
    ابÙĩ
    -0.06
    QUIRES
    -0.06
     aValue
    -0.06
    é¾
    -0.06
    zier
    -0.06
    POSITIVE LOGITS
    626
    0.07
    ød
    0.06
     uk
    0.06
    Ìĥ
    0.06
     amp
    0.06
    628
    0.06
    ruk
    0.06
    752
    0.06
    /goto
    0.06
    617
    0.06
    Activations Density 0.001%

    No Known Activations