© 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 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. 85307
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to institutional and community governance

    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
     ìŬ룬ë¶Ħ
    -0.07
    zos
    -0.07
    alice
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.06
    adaÅŁ
    -0.06
     Warn
    -0.06
    ammable
    -0.06
    inho
    -0.06
     Americas
    -0.06
     InitializeComponent
    -0.06
    POSITIVE LOGITS
    ãĥIJãĥ¼
    0.07
     Kür
    0.06
     Morm
    0.06
    pper
    0.06
    úsqueda
    0.06
    ertino
    0.06
    oooooooo
    0.06
    fila
    0.06
    είο
    0.06
    اا
    0.06
    Activations Density 0.004%

    No Known Activations