© 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. 2056
    Prev
    Next
    INDEX
    Explanations

    concepts related to student agency and educational practices

    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
    ominator
    -0.07
    åħ¬åijĬ
    -0.06
    ugin
    -0.06
     Smoke
    -0.06
    ween
    -0.06
    azen
    -0.06
    UGIN
    -0.06
    à¹Ĥà¸Ĺร
    -0.06
    oso
    -0.06
     Sever
    -0.06
    POSITIVE LOGITS
    ynchronous
    0.07
     summ
    0.07
    iture
    0.06
     tang
    0.06
     lak
    0.06
    rek
    0.06
    inger
    0.06
    нÑı
    0.06
    oft
    0.05
    CTL
    0.05
    Activations Density 0.002%

    No Known Activations