© 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. 106224
    Prev
    Next
    INDEX
    Explanations

    procedural and regulatory language related to processes or tasks

    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
    eza
    -0.06
    ample
    -0.06
    oster
    -0.06
    ville
    -0.06
     finally
    -0.06
    auge
    -0.06
    ama
    -0.06
    isel
    -0.06
    heim
    -0.06
    esa
    -0.06
    POSITIVE LOGITS
     separate
    0.15
     Separate
    0.13
     seperate
    0.13
     separately
    0.13
     ayrı
    0.09
    Separ
    0.09
     separ
    0.09
     оÑĤделÑĮ
    0.09
     samostat
    0.08
     independ
    0.08
    Activations Density 0.023%

    No Known Activations