© 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. 4813
    Prev
    Next
    INDEX
    Explanations

    information about geographical areas and their measurements

    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
     Views
    -0.06
    LOCAL
    -0.06
    ustral
    -0.06
     unb
    -0.06
    .community
    -0.06
     southwestern
    -0.06
     tight
    -0.06
    лаз
    -0.06
    osg
    -0.06
     community
    -0.06
    POSITIVE LOGITS
     land
    0.09
    otland
    0.08
    _land
    0.08
     createState
    0.08
     Äijất
    0.07
    ilen
    0.07
     surface
    0.07
    akis
    0.07
    ountry
    0.07
    _lit
    0.07
    Activations Density 0.011%

    No Known Activations