© 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. 123712
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational structures and positions

    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
    _FAULT
    -0.07
     Dome
    -0.07
    inue
    -0.06
    лиÑĨ
    -0.06
     nett
    -0.06
     serie
    -0.06
    اÙĪر
    -0.06
     поба
    -0.06
    λιά
    -0.06
     Tage
    -0.06
    POSITIVE LOGITS
     today
    0.07
     yesterday
    0.07
     dated
    0.07
     пÑĥÑĤем
    0.07
     via
    0.07
    ORB
    0.06
    mant
    0.06
    æĺ¨
    0.06
    ücken
    0.06
     effective
    0.06
    Activations Density 0.027%

    No Known Activations