© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107068
    Prev
    Next
    INDEX
    Explanations

    terms related to caregiving roles within a community

    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
     specifically
    -0.06
     Zuk
    -0.06
    ='".
    -0.06
    uitka
    -0.06
    åħĦ
    -0.06
     Nach
    -0.06
     å¯
    -0.06
     predicate
    -0.06
     SUN
    -0.06
    AILS
    -0.06
    POSITIVE LOGITS
    биÑĤ
    0.07
    vice
    0.07
    bles
    0.07
    κά
    0.07
    OMEM
    0.07
    æĻĤ代
    0.07
    _enum
    0.06
    jez
    0.06
    bonus
    0.06
     Knock
    0.06
    Activations Density 0.000%

    No Known Activations