© 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. 5151
    Prev
    Next
    INDEX
    Explanations

    terms related to network states and conditions, particularly regarding whether a link or process is active or inactive

    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
    .infinity
    -0.08
    agt
    -0.07
    ennie
    -0.07
    .mutable
    -0.07
    lemen
    -0.07
    ÙĦاÙħ
    -0.06
    каж
    -0.06
     yourselves
    -0.06
    arga
    -0.06
    rame
    -0.06
    POSITIVE LOGITS
     (
    0.07
    .grade
    0.07
    илÑı
    0.07
    inja
    0.06
    sil
    0.06
     (`
    0.06
     yani
    0.06
     meaning
    0.06
    plib
    0.06
     determined
    0.05
    Activations Density 0.058%

    No Known Activations