© 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. 105821
    Prev
    Next
    INDEX
    Explanations

    references to insects and their ecological behaviors

    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
    ensem
    -0.08
     Roses
    -0.07
    лÑĥÑĩ
    -0.06
    ingt
    -0.06
     Campus
    -0.06
    aukee
    -0.06
    awe
    -0.06
    ábado
    -0.06
    quine
    -0.06
     birds
    -0.06
    POSITIVE LOGITS
    Å¡ov
    0.07
    /cop
    0.06
     bonded
    0.06
     piv
    0.06
    oined
    0.06
    /Error
    0.06
    apter
    0.06
    충
    0.06
    reten
    0.06
    javascript
    0.06
    Activations Density 0.003%

    No Known Activations