© 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. 14996
    Prev
    Next
    INDEX
    Explanations

    terms related to expansion and growth in various contexts

    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
    ched
    -0.07
     beyond
    -0.07
     scope
    -0.06
    oss
    -0.06
    uti
    -0.06
    pagen
    -0.06
    Capabilities
    -0.06
    	freopen
    -0.06
    otten
    -0.06
     existing
    -0.06
    POSITIVE LOGITS
    apol
    0.07
    linkplain
    0.07
    sten
    0.07
    vÄĽd
    0.07
    aksi
    0.07
    sar
    0.07
    holm
    0.07
    uner
    0.07
    nda
    0.06
    ASY
    0.06
    Activations Density 0.008%

    No Known Activations