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. MLP Out
    5. 25-LLAMASCOPE-MLP-131K
    6. 72553
    Prev
    Next
    INDEX
    Explanations

    brackets or related symbols in text

    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
    Äįet
    -0.06
    Imports
    -0.06
     mo
    -0.06
    ега
    -0.06
    Ordinal
    -0.06
     Wax
    -0.06
    ạch
    -0.06
     Jos
    -0.06
     ad
    -0.06
    &&(
    -0.06
    POSITIVE LOGITS
    hani
    0.08
    indle
    0.07
    igor
    0.07
    shit
    0.06
    ile
    0.06
    aru
    0.06
    ung
    0.06
    itar
    0.06
    rape
    0.06
    оÑĢов
    0.06
    Activations Density 0.025%

    No Known Activations