© 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. 61809
    Prev
    Next
    INDEX
    Explanations

    affirmations of positive feelings or experiences

    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
    aub
    -0.07
     zenith
    -0.07
    aching
    -0.07
    unga
    -0.07
    ALLERY
    -0.07
    íĥĪ
    -0.07
    andin
    -0.07
    uhan
    -0.07
    alet
    -0.07
    inks
    -0.06
    POSITIVE LOGITS
     immedi
    0.06
    į
    0.06
     it
    0.06
     immediately
    0.06
     sho
    0.06
     just
    0.06
    kee
    0.06
     immediate
    0.06
    asha
    0.06
     absolutely
    0.06
    Activations Density 0.049%

    No Known Activations