© 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 EvalsExportsAPI 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. 88700
    Prev
    Next
    INDEX
    Explanations

    concepts related to support and mentorship within family and community structures

    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
    stri
    -0.08
    ä¸Ī夫
    -0.07
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    -0.07
    okud
    -0.07
    INO
    -0.07
    anka
    -0.07
    ardin
    -0.07
    mdir
    -0.07
    deo
    -0.07
    å©
    -0.07
    POSITIVE LOGITS
     mentor
    0.09
     mentoring
    0.08
     pat
    0.08
     care
    0.07
     ment
    0.07
     Mentor
    0.07
     substitute
    0.07
     Ment
    0.07
     surrogate
    0.06
     unofficial
    0.06
    Activations Density 0.088%

    No Known Activations