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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5000
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Tow" or "tow" in various 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
    ieres
    -0.07
    -spe
    -0.06
     Arch
    -0.06
    moid
    -0.06
    ipi
    -0.06
     bare
    -0.06
     mot
    -0.06
    _timing
    -0.06
     Ariel
    -0.06
    opsis
    -0.06
    POSITIVE LOGITS
    elight
    0.07
    headed
    0.07
    .XR
    0.07
    Cause
    0.07
     tang
    0.07
    omba
    0.07
    annt
    0.07
    Lifetime
    0.06
    iche
    0.06
    312
    0.06
    Activations Density 0.001%

    No Known Activations