© 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. 108145
    Prev
    Next
    INDEX
    Explanations

    recurring elements and patterns in processes or systems

    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
    kar
    -0.07
    iley
    -0.07
    nen
    -0.06
    iful
    -0.06
     passive
    -0.06
    ød
    -0.06
     Pas
    -0.06
    orth
    -0.06
    eterangan
    -0.06
    ác
    -0.06
    POSITIVE LOGITS
    ë§Īëĭ¤
    0.11
     EACH
    0.09
    each
    0.09
     each
    0.09
    æ¯ı
    0.08
     каждого
    0.08
    _each
    0.08
    Each
    0.08
     кажд
    0.08
     æ¯ı
    0.07
    Activations Density 0.013%

    No Known Activations