© 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. 17-LLAMASCOPE-RES-131K
    11. 80334
    Prev
    Next
    INDEX
    Explanations

    terms related to indirect measurements and discharges in environmental contexts

    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
    endale
    -0.07
    ãĤ¤ãĥĦ
    -0.07
    æł·çļĦ
    -0.07
    IFIC
    -0.07
    _AST
    -0.07
    plat
    -0.07
    Æ°á»Ľ
    -0.07
    çak
    -0.07
    bÃŃ
    -0.07
    ارÛĮ
    -0.07
    POSITIVE LOGITS
     indirect
    0.10
     INDIRECT
    0.09
    s
    0.08
    ively
    0.08
    irect
    0.08
    ives
    0.08
    ely
    0.08
    -direct
    0.08
    ive
    0.07
     indirectly
    0.07
    Activations Density 0.006%

    No Known Activations