© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 26674
    Prev
    Next
    INDEX
    Explanations

    concepts related to organizational practices and commercial strategies

    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
    лÑĥ
    -0.07
    borough
    -0.06
    rena
    -0.06
    æ¡IJ
    -0.06
    owie
    -0.06
    cam
    -0.06
    aras
    -0.06
    ιο
    -0.06
    zahl
    -0.06
    .ul
    -0.05
    POSITIVE LOGITS
    ä¸įäºĨ
    0.07
     Kens
    0.07
    boys
    0.07
    iken
    0.07
     consect
    0.07
    Pragma
    0.07
    ernels
    0.07
    ign
    0.07
    VELO
    0.07
     кÑĥлÑĮ
    0.07
    Activations Density 0.033%

    No Known Activations