© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74578
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and settlements

    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
    orget
    -0.07
    iaux
    -0.07
    arin
    -0.07
    ekl
    -0.07
    _Impl
    -0.07
    edium
    -0.06
    -www
    -0.06
     aks
    -0.06
    Introduced
    -0.06
     Epoch
    -0.06
    POSITIVE LOGITS
    onu
    0.07
     dne
    0.07
     tod
    0.07
    today
    0.07
     today
    0.07
    (today
    0.07
    bundles
    0.06
    yas
    0.06
     later
    0.06
    bundle
    0.06
    Activations Density 0.029%

    No Known Activations