© 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. 54709
    Prev
    Next
    INDEX
    Explanations

    specific terms related to historical settlements and communities

    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
    reh
    -0.09
    ÑĢÑı
    -0.07
    [".
    -0.07
    à¸²à¸Ł
    -0.07
    &action
    -0.07
    اÙħÛĮÙĨ
    -0.06
    FileVersion
    -0.06
    //{{
    -0.06
    lpVtbl
    -0.06
    .NotNil
    -0.06
    POSITIVE LOGITS
     territory
    0.07
    ante
    0.07
     Autos
    0.06
     apost
    0.06
     splits
    0.06
    åĺ
    0.06
    isl
    0.06
    ANTE
    0.06
     split
    0.06
     Gunn
    0.06
    Activations Density 0.001%

    No Known Activations