© 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. 77277
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS properties related to borders

    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
    æĸĹ
    -0.08
    меÑī
    -0.07
    ä½
    -0.07
    ristol
    -0.07
    osal
    -0.07
     диамеÑĤ
    -0.07
    enschaft
    -0.07
    ependency
    -0.07
    Ñģим
    -0.07
    å´İ
    -0.07
    POSITIVE LOGITS
    骨
    0.06
    0.06
    less
    0.06
    mer
    0.06
    lose
    0.06
    chan
    0.06
    los
    0.05
    0
    0.05
    atl
    0.05
    arin
    0.05
    Activations Density 0.003%

    No Known Activations