Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43500
    Prev
    Next
    INDEX
    Explanations

    phrases related to setting goals and aspirations

    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
     zdrav
    -0.08
     odense
    -0.08
     echang
    -0.07
     aalborg
    -0.07
    @nate
    -0.07
     geschichten
    -0.07
    _firestore
    -0.07
     weiber
    -0.07
    frey
    -0.07
     prostituerade
    -0.06
    POSITIVE LOGITS
     wan
    0.09
     gad
    0.09
    mu
    0.09
     anak
    0.09
     ister
    0.08
     ib
    0.08
    ku
    0.08
     mereka
    0.08
     orang
    0.08
     itu
    0.08
    Activations Density 0.005%

    No Known Activations