© 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. 70397
    Prev
    Next
    INDEX
    Explanations

    expressions of intent and purpose regarding personal or communal objectives

    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
    ãģªãģĮãĤī
    -0.07
    echan
    -0.06
     Yap
    -0.06
    hwnd
    -0.06
    Äĥr
    -0.06
    ichte
    -0.06
    IfNeeded
    -0.06
    lena
    -0.06
    tha
    -0.06
    icht
    -0.06
    POSITIVE LOGITS
     focus
    0.11
    focus
    0.11
    Focus
    0.09
     Focus
    0.09
     focuses
    0.09
     specifically
    0.09
    -focus
    0.09
    .focus
    0.09
     foc
    0.08
     focusing
    0.08
    Activations Density 0.023%

    No Known Activations