© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89851
    Prev
    Next
    INDEX
    Explanations

    terms related to firefighting and water usage in urban environments

    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
    986
    -0.07
    andin
    -0.06
     Razor
    -0.06
     Ze
    -0.06
    inx
    -0.06
     fug
    -0.05
    enz
    -0.05
    è¨ĢãģĦ
    -0.05
    ennai
    -0.05
     sex
    -0.05
    POSITIVE LOGITS
    (æ°´
    0.09
    åĿĬ
    0.08
    egot
    0.07
     effectiveness
    0.07
    ữu
    0.07
     spraying
    0.07
    ÄĽt
    0.07
     góc
    0.07
    (çģ«
    0.07
    æ»ħ
    0.07
    Activations Density 0.005%

    No Known Activations