© 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. 16500
    Prev
    Next
    INDEX
    Explanations

    references to governmental or regulatory processes and documents

    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
    tier
    -0.06
    ritz
    -0.06
    hya
    -0.06
    inded
    -0.06
     Glenn
    -0.06
    pte
    -0.06
    agen
    -0.06
    LF
    -0.06
    /*!↵
    -0.05
    ç¸
    -0.05
    POSITIVE LOGITS
     âĹĦ
    0.08
    ç»į
    0.07
    .DataTable
    0.07
     circular
    0.07
    Circular
    0.07
    #
    0.07
    vice
    0.07
    تÙĨ
    0.07
    ramework
    0.07
    utow
    0.07
    Activations Density 0.004%

    No Known Activations