© 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. 56102
    Prev
    Next
    INDEX
    Explanations

    phrases expressing commitment and readiness to provide services

    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
    lector
    -0.07
    ffi
    -0.07
     itself
    -0.06
    pter
    -0.06
    å°ģ
    -0.06
     Liberties
    -0.06
    ÑĨии
    -0.06
    orage
    -0.06
    sein
    -0.06
    ofilm
    -0.05
    POSITIVE LOGITS
    CTL
    0.07
    sÃŃ
    0.07
    #ad
    0.07
    θη
    0.07
    .flex
    0.07
    rollo
    0.07
    ä¹ħ
    0.07
    _gui
    0.07
    ImGui
    0.06
     Chill
    0.06
    Activations Density 0.017%

    No Known Activations