© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 81350
    Prev
    Next
    INDEX
    Explanations

    scientific terms and methodologies related to cellular biology and laboratory assays

    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
    /ion
    -0.07
    bnb
    -0.06
    INF
    -0.06
     Jaime
    -0.06
    _framework
    -0.06
    .TEXTURE
    -0.06
    lage
    -0.06
    buah
    -0.06
    ома
    -0.06
    ibus
    -0.06
    POSITIVE LOGITS
     exc
    0.08
     dye
    0.07
    .marker
    0.07
    æŁĵ
    0.07
    Intensity
    0.07
    quoise
    0.06
     images
    0.06
    ashes
    0.06
     excited
    0.06
     För
    0.06
    Activations Density 0.010%

    No Known Activations