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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 70992
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to geographic features and environmental concepts

    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
     of
    -0.07
    iger
    -0.07
     stav
    -0.06
     Nack
    -0.06
    qry
    -0.06
     же
    -0.06
    clin
    -0.06
    ikler
    -0.06
    ê¸°ë¡ľ
    -0.06
    iko
    -0.06
    POSITIVE LOGITS
    parator
    0.08
     ÛĮعÙĨÛĮ
    0.08
    endcode
    0.07
    .googlecode
    0.07
    quee
    0.07
    \Blueprint
    0.07
    alom
    0.07
    DataExchange
    0.07
    #endregion
    0.07
    CppClass
    0.07
    Activations Density 0.106%

    No Known Activations