© 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. 130173
    Prev
    Next
    INDEX
    Explanations

    terms related to physicality and experience

    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
    itur
    -0.07
    resizing
    -0.07
    avanaugh
    -0.07
    onte
    -0.07
    ')['
    -0.06
    usercontent
    -0.06
    ucch
    -0.06
    екÑĤÑĥ
    -0.06
    amaz
    -0.06
     Kerry
    -0.06
    POSITIVE LOGITS
     or
    0.20
     lẫn
    0.15
     или
    0.15
     ÛĮا
    0.14
    æĪĸ
    0.14
     ëĺIJëĬĶ
    0.14
    ãģ¾ãģŁãģ¯
    0.13
    æĪĸèĢħ
    0.13
     vs
    0.13
     versus
    0.13
    Activations Density 0.229%

    No Known Activations