© 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. 125341
    Prev
    Next
    INDEX
    Explanations

    concepts related to access to energy and its impact on community resources

    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
    taÅŁ
    -0.08
     priv
    -0.07
     Bour
    -0.07
    ober
    -0.06
     Priv
    -0.06
     softball
    -0.06
     duct
    -0.06
     Bos
    -0.06
     exh
    -0.06
    raki
    -0.06
    POSITIVE LOGITS
     Charge
    0.07
    TRS
    0.07
    Wiki
    0.06
    okino
    0.06
    acie
    0.06
     loadData
    0.06
     power
    0.06
     electronic
    0.06
    ammer
    0.06
    urve
    0.06
    Activations Density 0.034%

    No Known Activations