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. 43805
    Prev
    Next
    INDEX
    Explanations

    expressions related to gaming and leisure activities

    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
     salopes
    -0.07
    leftright
    -0.07
     ragaz
    -0.07
    ÏĩεδÏĮν
    -0.07
     Hizmetleri
    -0.07
    ombine
    -0.07
     sourceMapping
    -0.07
    دÙĪØ§Ø¬
    -0.07
     pornofil
    -0.07
    oldem
    -0.07
    POSITIVE LOGITS
     amazing
    0.16
     magnificent
    0.16
     wonderful
    0.16
     impressive
    0.16
     fantastic
    0.16
     incredible
    0.16
     brilliant
    0.15
     marvelous
    0.15
     remarkable
    0.15
     fascinating
    0.15
    Activations Density 13.649%

    No Known Activations