© 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. 5-LLAMASCOPE-RES-131K
    11. 125767
    Prev
    Next
    INDEX
    Explanations

    references to user interfaces or programming elements

    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
    oon
    -0.07
     McCoy
    -0.07
    lap
    -0.07
    tek
    -0.07
    gili
    -0.06
    achs
    -0.06
    _DISP
    -0.06
    arat
    -0.06
    antro
    -0.06
    curso
    -0.06
    POSITIVE LOGITS
     Bundle
    0.07
    Bundle
    0.07
    .bundle
    0.07
     bundle
    0.07
    uxtap
    0.06
    .Bundle
    0.06
    iseum
    0.06
    &view
    0.06
     Obl
    0.06
    htmlspecialchars
    0.06
    Activations Density 0.000%

    No Known Activations