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. 43790
    Prev
    Next
    INDEX
    Explanations

    keywords and identifiers related to the Java programming language

    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
    lander
    -0.06
    &page
    -0.06
     exceptions
    -0.06
    «a
    -0.05
    оÑĢм
    -0.05
     Everyday
    -0.05
     INT
    -0.05
    elt
    -0.05
    views
    -0.05
    onta
    -0.05
    POSITIVE LOGITS
    .util
    0.17
    /util
    0.14
    _util
    0.12
     utility
    0.11
    _UTIL
    0.10
     util
    0.10
    _utilities
    0.10
    .utilities
    0.10
    	util
    0.09
     utilities
    0.09
    Activations Density 0.003%

    No Known Activations