© 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. 29359
    Prev
    Next
    INDEX
    Explanations

    regulatory terms and applications related to permits and provisions

    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
    ÙģصÙĦ
    -0.07
    ordova
    -0.06
    anko
    -0.06
    eil
    -0.06
    nof
    -0.06
    @example
    -0.06
    ritte
    -0.06
    enser
    -0.06
    ipated
    -0.06
    InThe
    -0.06
    POSITIVE LOGITS
     âĦĸ
    0.08
    (s
    0.08
     #
    0.07
    sto
    0.07
    (#)
    0.07
    laz
    0.07
     sá»ij
    0.07
    #:
    0.06
    #
    0.06
     ÄįÃŃslo
    0.06
    Activations Density 0.038%

    No Known Activations