© 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. 17-LLAMASCOPE-RES-131K
    11. 81765
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical equivalence and 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
    ำ
    -0.07
    ewire
    -0.07
     PropertyChangedEventArgs
    -0.07
    AxisSize
    -0.07
    hcp
    -0.07
    Creators
    -0.07
    à¸Ĥว
    -0.07
     subsidi
    -0.07
     sublic
    -0.07
    otron
    -0.07
    POSITIVE LOGITS
     equivalence
    0.08
     representatives
    0.07
     representative
    0.07
     pairs
    0.06
    umber
    0.06
     represented
    0.06
     group
    0.06
    GER
    0.06
     o
    0.06
    INGTON
    0.05
    Activations Density 0.087%

    No Known Activations