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

    Neuronpedia

    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. 55599
    Prev
    Next
    INDEX
    Explanations

    programming structures and calculations related to geometry

    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
    Äħż
    -0.07
    561
    -0.07
    znik
    -0.07
    zman
    -0.07
    ãĥ¼ãĥľ
    -0.07
    arda
    -0.07
    bern
    -0.06
    auge
    -0.06
    348
    -0.06
    oes
    -0.06
    POSITIVE LOGITS
    apest
    0.07
     edition
    0.06
     Morrow
    0.06
    ima
    0.06
    overflow
    0.06
    ataka
    0.06
    à¸ĵ
    0.06
    terior
    0.06
    eyh
    0.06
     Managed
    0.05
    Activations Density 0.030%

    No Known Activations