© 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. 84336
    Prev
    Next
    INDEX
    Explanations

    financial terms related to reserves and endowments

    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
    vou
    -0.07
    HEMA
    -0.07
    rench
    -0.06
    zell
    -0.06
    .nick
    -0.06
     zev
    -0.06
    _UID
    -0.06
    endet
    -0.06
    aná
    -0.06
     ÙĪØŃدة
    -0.06
    POSITIVE LOGITS
     stores
    0.09
     contents
    0.08
     chứa
    0.08
     storing
    0.07
    enant
    0.07
     Grow
    0.07
     management
    0.07
     bank
    0.07
     lag
    0.07
     created
    0.07
    Activations Density 0.066%

    No Known Activations