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. 22-LLAMASCOPE-RES-131K
    6. 5765
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and resilience

    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
    orman
    -0.07
    ultan
    -0.07
    indow
    -0.07
    ÙģØ§Øª
    -0.07
    atte
    -0.06
    Locker
    -0.06
    atts
    -0.06
     insensitive
    -0.06
    orz
    -0.06
    quets
    -0.06
    POSITIVE LOGITS
     spaces
    0.07
    esson
    0.07
     collective
    0.07
     Survivor
    0.07
     queer
    0.06
     Indigenous
    0.06
     survivor
    0.06
     fucking
    0.06
     intersection
    0.06
     Collective
    0.06
    Activations Density 0.018%

    No Known Activations