© 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. 130264
    Prev
    Next
    INDEX
    Explanations

    concepts related to scholarship opportunities and pathways in a specific context

    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
     ARGS
    -0.06
    ãĤıãģij
    -0.06
    iej
    -0.06
    ElementsBy
    -0.06
     Iso
    -0.06
    itta
    -0.06
    иной
    -0.06
    _manifest
    -0.06
    -distance
    -0.06
    èĮĥ
    -0.06
    POSITIVE LOGITS
     transition
    0.09
     eventual
    0.09
    transition
    0.08
     convertible
    0.08
     gateway
    0.08
     later
    0.08
     conversions
    0.08
    .intellij
    0.08
     conversion
    0.08
     Gateway
    0.08
    Activations Density 0.034%

    No Known Activations