© 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. 1661
    Prev
    Next
    INDEX
    Explanations

    expressions related to time management and family interactions

    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
    eri
    -0.06
    rale
    -0.06
    otte
    -0.06
    osg
    -0.06
    utan
    -0.06
    /if
    -0.06
     Circular
    -0.06
    омен
    -0.06
    tees
    -0.06
     circular
    -0.06
    POSITIVE LOGITS
     time
    0.09
    Zone
    0.08
     space
    0.08
     moments
    0.07
     zones
    0.07
     quiet
    0.07
    空éĹ´
    0.07
     bond
    0.07
    space
    0.07
     retreat
    0.07
    Activations Density 0.060%

    No Known Activations