© 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. 107066
    Prev
    Next
    INDEX
    Explanations

    terms related to openings or voids in physical structures

    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
    æ³Ĭ
    -0.08
    utc
    -0.07
    _attached
    -0.07
     Yap
    -0.06
    ubby
    -0.06
    ainment
    -0.06
    .onStart
    -0.06
    ut
    -0.06
     Werner
    -0.06
    caff
    -0.06
    POSITIVE LOGITS
     formed
    0.09
     created
    0.09
     opening
    0.08
     opened
    0.08
    -opening
    0.08
    /open
    0.07
    opened
    0.07
     filled
    0.07
    ills
    0.07
    lli
    0.07
    Activations Density 0.073%

    No Known Activations