© 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. 17831
    Prev
    Next
    INDEX
    Explanations

    terms associated with gaming, technology, and health-related subjects

    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
    âĢİ
    -0.08
    -Ass
    -0.06
    [d
    -0.06
    -0.06
    :UIControl
    -0.06
    _cmos
    -0.06
     Fro
    -0.05
    ]âĢı
    -0.05
    âĶ¬
    -0.05
    outh
    -0.05
    POSITIVE LOGITS
    -related
    0.09
    EIF
    0.08
    Ordinal
    0.08
    afb
    0.07
    ccd
    0.07
    RenderingContext
    0.07
    Century
    0.07
    DITION
    0.07
    ylation
    0.07
    related
    0.07
    Activations Density 0.041%

    No Known Activations