© 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. 17-LLAMASCOPE-RES-131K
    11. 129547
    Prev
    Next
    INDEX
    Explanations

    mentions of charter schools and discussions around educational institutions

    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
    ä¿ĿéĻ©
    -0.07
    akte
    -0.07
    _marshall
    -0.07
    marshall
    -0.07
    ryo
    -0.07
    	Copyright
    -0.07
    imen
    -0.07
     discrepan
    -0.06
    ritch
    -0.06
    ëĮĢíĸī
    -0.06
    POSITIVE LOGITS
     charter
    0.08
    char
    0.07
     Charter
    0.07
     transparent
    0.06
    ân
    0.06
    operator
    0.06
     ops
    0.06
     open
    0.06
     growth
    0.06
     franch
    0.06
    Activations Density 0.004%

    No Known Activations