© 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. 81588
    Prev
    Next
    INDEX
    Explanations

    references to question types and properties of assessments

    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
     amat
    -0.07
    berger
    -0.07
    PLL
    -0.07
     luder
    -0.07
    ìĹ´
    -0.07
    \application
    -0.06
    .Debugger
    -0.06
     cmdline
    -0.06
    UrlParser
    -0.06
    è¿ij
    -0.06
    POSITIVE LOGITS
     Whereas
    0.08
     others
    0.08
     whereas
    0.08
     ones
    0.07
    ramer
    0.06
    çļĦæĺ¯
    0.06
    uner
    0.06
    oux
    0.06
    others
    0.06
     же
    0.06
    Activations Density 0.021%

    No Known Activations