© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94357
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical properties and metrics in graph theory

    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
    assen
    -0.07
    agi
    -0.06
     Goth
    -0.06
     felt
    -0.06
    ALE
    -0.06
     jewel
    -0.06
    oor
    -0.06
    elta
    -0.06
    indi
    -0.06
    iaux
    -0.06
    POSITIVE LOGITS
    iosis
    0.07
    vrd
    0.07
    EK
    0.06
     Ø®ÙĪر
    0.06
    613
    0.06
    .createComponent
    0.06
    AndView
    0.06
    ughty
    0.06
    .scalablytyped
    0.06
    ACHI
    0.06
    Activations Density 0.028%

    No Known Activations