© 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. 15-LLAMASCOPE-RES-131K
    11. 88688
    Prev
    Next
    INDEX
    Explanations

    commands or instructions related to navigating a system or process

    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
     invariant
    -0.07
    iaux
    -0.07
    егоÑĢ
    -0.06
    peq
    -0.06
    msp
    -0.06
    ÑĪе
    -0.06
    acies
    -0.06
     Gale
    -0.06
    olie
    -0.06
     phenomen
    -0.06
    POSITIVE LOGITS
    stad
    0.07
    eba
    0.06
    akk
    0.06
    _unused
    0.06
     либо
    0.06
     then
    0.06
    pageTitle
    0.06
    Breadcrumb
    0.06
    θή
    0.06
     Kron
    0.06
    Activations Density 0.021%

    No Known Activations