© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62214
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intention related to attending, offering, or updating events or programs

    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
     unh
    -0.06
    enth
    -0.06
    12
    -0.06
    word
    -0.06
     Gh
    -0.05
     Cin
    -0.05
    en
    -0.05
    ll
    -0.05
    yc
    -0.05
    ly
    -0.05
    POSITIVE LOGITS
    auga
    0.07
    ãĥ©ãĤ¹
    0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.07
    imdi
    0.07
    ког
    0.07
    лоб
    0.07
    iola
    0.07
    .weixin
    0.07
    Ỽ
    0.07
    educt
    0.07
    Activations Density 0.017%

    No Known Activations