© 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. 130413
    Prev
    Next
    INDEX
    Explanations

    usages of the term "use of."

    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
    oci
    -0.07
    ãĥ¼ãĤ¹
    -0.07
    åĨµ
    -0.06
    quist
    -0.06
    apore
    -0.06
    329
    -0.06
    ç·´
    -0.06
    eri
    -0.06
    rophe
    -0.06
    ammen
    -0.06
    POSITIVE LOGITS
    èĵ
    0.07
    dech
    0.07
    DT
    0.07
    prises
    0.06
    ynchronously
    0.06
     Wilkinson
    0.06
    BY
    0.06
    رÙĪت
    0.06
    Marca
    0.06
    abyrinth
    0.06
    Activations Density 0.003%

    No Known Activations