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. 29-LLAMASCOPE-MLP-131K
    6. 5066
    Prev
    Next
    INDEX
    Explanations

    words related to academic or scientific terminology

    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
    usk
    -0.07
    ôt
    -0.07
    subst
    -0.06
     æ¥
    -0.06
     Joyce
    -0.06
    ICY
    -0.06
    ois
    -0.06
    cela
    -0.06
     quad
    -0.06
    Quad
    -0.06
    POSITIVE LOGITS
     Ment
    0.07
    eron
    0.06
    orre
    0.06
     nob
    0.06
    ĽĦ
    0.06
     Mental
    0.06
    endl
    0.06
     Kür
    0.06
    319
    0.06
    idal
    0.06
    Activations Density 0.000%

    No Known Activations