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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106286
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "const" in programming contexts

    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
    wig
    -0.07
     ↵↵
    -0.07
    wright
    -0.07
     eiusmod
    -0.07
    weed
    -0.07
    bras
    -0.07
    urd
    -0.07
    _gettime
    -0.06
    urs
    -0.06
    ett
    -0.06
    POSITIVE LOGITS
     char
    0.07
    entiful
    0.07
    adele
    0.06
    _iterator
    0.06
    /legal
    0.06
    antro
    0.06
    itle
    0.06
     Miner
    0.06
    ãĤ«ãĥ¼
    0.06
    eniable
    0.06
    Activations Density 0.007%

    No Known Activations