© 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. 9-LLAMASCOPE-RES-131K
    11. 97943
    Prev
    Next
    INDEX
    Explanations

    references to verses in religious texts

    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
    te
    -0.09
    agua
    -0.07
    rippling
    -0.07
    iske
    -0.07
    ãģ¾ãģŁ
    -0.07
    side
    -0.07
    tee
    -0.07
    ten
    -0.07
    itary
    -0.06
    k
    -0.06
    POSITIVE LOGITS
    icher
    0.08
    PointF
    0.07
    batim
    0.07
    ãģªãģĦ
    0.07
    illance
    0.07
    eniable
    0.07
    à¸Ńà¸Ł
    0.07
    mith
    0.07
    anging
    0.07
    iy
    0.07
    Activations Density 0.020%

    No Known Activations