© 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. 124462
    Prev
    Next
    INDEX
    Explanations

    references to potential solutions, workarounds, or methods to address problems

    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
    sert
    -0.07
    ÏĦί
    -0.06
    uzz
    -0.06
    aten
    -0.06
    ingers
    -0.06
    ê²°
    -0.06
    /DD
    -0.06
    .Mutable
    -0.06
     øns
    -0.06
    Jac
    -0.06
    POSITIVE LOGITS
     solution
    0.08
     option
    0.07
     Solution
    0.07
     suggestion
    0.07
     viable
    0.07
     would
    0.07
    Solution
    0.07
     Option
    0.07
     solutions
    0.07
     involves
    0.07
    Activations Density 0.035%

    No Known Activations