© 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. 71324
    Prev
    Next
    INDEX
    Explanations

    materials and structural elements in a description

    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
    akis
    -0.07
    âĦ
    -0.06
    gings
    -0.06
    à¸Ľà¸£à¸°à¸ª
    -0.06
     æĿ¾
    -0.06
    *size
    -0.06
    chts
    -0.06
    /themes
    -0.06
    comings
    -0.06
    cribe
    -0.06
    POSITIVE LOGITS
    ized
    0.09
    -based
    0.09
    isia
    0.08
    -backed
    0.08
    -Based
    0.08
    -lined
    0.07
    -covered
    0.07
    /html
    0.07
    reste
    0.07
    /pl
    0.07
    Activations Density 0.032%

    No Known Activations