© 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. 117395
    Prev
    Next
    INDEX
    Explanations

    specific terms related to location and geography

    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
    enza
    -0.08
    mmo
    -0.06
     Weg
    -0.06
     uranus
    -0.06
    571
    -0.06
    inth
    -0.06
    hill
    -0.06
    464
    -0.06
    MSC
    -0.06
     saturn
    -0.06
    POSITIVE LOGITS
     Dickinson
    0.07
    μείο
    0.07
     Bilim
    0.07
     αÏħÏĦά
    0.07
    amera
    0.07
    alia
    0.07
    lej
    0.07
    gment
    0.07
     Unternehmen
    0.06
    aug
    0.06
    Activations Density 0.039%

    No Known Activations