© 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. 105161
    Prev
    Next
    INDEX
    Explanations

    references to biblical or scriptural citations

    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
     reserved
    -0.06
    ellation
    -0.06
     fit
    -0.06
     Co
    -0.05
     Cap
    -0.05
    :
    -0.05
    DebugEnabled
    -0.05
    olid
    -0.05
     solid
    -0.05
     and
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĤ¸
    0.08
    addock
    0.07
    FML
    0.07
     sebe
    0.07
    ÏĢοÏĦε
    0.07
    (formatter
    0.07
    ë£
    0.07
    LOGGER
    0.07
    anos
    0.07
    ValueCollection
    0.07
    Activations Density 0.004%

    No Known Activations