© 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. 79104
    Prev
    Next
    INDEX
    Explanations

    concepts related to waste management and processing

    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
    ëĭĺìĿ´
    -0.06
     =========================================================================
    -0.06
    declspec
    -0.06
    REFER
    -0.06
    incinn
    -0.06
    å¼ı
    -0.06
     N
    -0.06
    est
    -0.05
     lái
    -0.05
    è²
    -0.05
    POSITIVE LOGITS
    system
    0.07
     priorities
    0.07
    okia
    0.06
    kaz
    0.06
    ktor
    0.06
    _filt
    0.06
     presence
    0.06
    slaught
    0.06
    idence
    0.06
     experience
    0.06
    Activations Density 0.055%

    No Known Activations