© 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. 107582
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to locations

    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
    aggi
    -0.07
     Sawyer
    -0.07
    è¥
    -0.07
    кин
    -0.07
    Jacob
    -0.07
    uros
    -0.07
    ادگÛĮ
    -0.07
    ÏĥÏĦ
    -0.07
    undan
    -0.07
    gar
    -0.06
    POSITIVE LOGITS
    åĪ»
    0.06
     Recon
    0.06
     balanced
    0.06
    ungi
    0.05
    -has
    0.05
     bang
    0.05
    Impl
    0.05
    Ī
    0.05
     drop
    0.05
     both
    0.05
    Activations Density 0.004%

    No Known Activations