© 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. 15-LLAMASCOPE-RES-131K
    11. 86821
    Prev
    Next
    INDEX
    Explanations

    terms related to educational programming and nonprofit organizations

    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
    ullet
    -0.07
    anian
    -0.07
    igs
    -0.07
    ements
    -0.07
    ipping
    -0.06
    RYPTO
    -0.06
    èı
    -0.06
    ë¬
    -0.06
    oria
    -0.06
    kup
    -0.06
    POSITIVE LOGITS
    dana
    0.07
    otton
    0.07
    ackers
    0.06
     experience
    0.06
    ë¡ľìĦľ
    0.06
    ingleton
    0.06
    anggan
    0.06
    emon
    0.06
    ieber
    0.06
    art
    0.06
    Activations Density 0.056%

    No Known Activations