© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60323
    Prev
    Next
    INDEX
    Explanations

    phrases related to agricultural practices and plant growth

    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
    vais
    -0.08
    à¸Ļà¹Ĩ
    -0.08
    raison
    -0.08
    ardon
    -0.08
    oÄį
    -0.08
    quine
    -0.07
    ebek
    -0.07
    culus
    -0.07
    ocu
    -0.07
    rof
    -0.07
    POSITIVE LOGITS
     â
    0.08
    â
    0.08
    :.
    0.07
     
    0.07
     ,
    0.06
     _____
    0.06
     coronavirus
    0.06
    в
    0.06
     âģ
    0.05
     video
    0.05
    Activations Density 0.051%

    No Known Activations