© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56910
    Prev
    Next
    INDEX
    Explanations

    concepts related to oscillation and fluctuation dynamics

    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
    isci
    -0.08
    flake
    -0.07
    olet
    -0.07
    γε
    -0.06
    isclosed
    -0.06
     Muse
    -0.06
    otu
    -0.06
     ancor
    -0.06
    ager
    -0.06
    essler
    -0.06
    POSITIVE LOGITS
    ancel
    0.08
    ations
    0.08
    ation
    0.08
    ante
    0.07
    ally
    0.07
    lep
    0.07
    ات
    0.07
    udes
    0.07
    avern
    0.07
    ingly
    0.07
    Activations Density 0.012%

    No Known Activations