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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 56428
    Prev
    Next
    INDEX
    Explanations

    terms related to isotropy and physical properties in scientific contexts

    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
    ood
    -0.07
    etre
    -0.07
    út
    -0.07
    holds
    -0.07
    ieces
    -0.07
    agt
    -0.07
     Silva
    -0.07
    .JMenuItem
    -0.07
    rary
    -0.06
    abox
    -0.06
    POSITIVE LOGITS
    /an
    0.06
    侯
    0.06
     Trilogy
    0.06
    ÙĦÙĥتر
    0.05
    /angular
    0.05
    گر
    0.05
    ylland
    0.05
    ness
    0.05
    Rnd
    0.05
    CompanyName
    0.05
    Activations Density 0.014%

    No Known Activations