© 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. 81767
    Prev
    Next
    INDEX
    Explanations

    terms related to boundaries and layers in a scientific context

    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
    748
    -0.06
    -filled
    -0.06
    //--------------------------------
    -0.06
     اÙĦج
    -0.06
    jer
    -0.06
    anium
    -0.05
     arousal
    -0.05
    icide
    -0.05
    itational
    -0.05
    headed
    -0.05
    POSITIVE LOGITS
    /interface
    0.09
    osal
    0.07
    dea
    0.07
    .Interface
    0.07
    -bound
    0.07
    /internal
    0.06
    -facing
    0.06
    -to
    0.06
    side
    0.06
    /head
    0.06
    Activations Density 0.035%

    No Known Activations