© 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. 40007
    Prev
    Next
    INDEX
    Explanations

    expressions related to staying, particularly at home and maintaining presence or care

    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
    isz
    -0.09
     Outlet
    -0.06
     outlets
    -0.06
    Äįas
    -0.06
     basket
    -0.06
    omon
    -0.06
    113
    -0.06
    ãĥ©ãĤ¹
    -0.06
    emey
    -0.05
    ategorie
    -0.05
    POSITIVE LOGITS
     longer
    0.10
     Longer
    0.08
    поÑģ
    0.07
    undef
    0.07
     Sanayi
    0.07
    senal
    0.07
     until
    0.07
     overnight
    0.07
    Until
    0.07
     pel
    0.07
    Activations Density 0.032%

    No Known Activations