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. 5039
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "still" 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
     even
    -0.10
     through
    -0.08
     Through
    -0.07
    uben
    -0.07
    through
    -0.07
    Through
    -0.07
    atica
    -0.07
    Us
    -0.07
     THROUGH
    -0.07
    even
    -0.06
    POSITIVE LOGITS
    alive
    0.07
     तह
    0.07
    æĻ
    0.07
    омÑĸ
    0.07
    ãĥĻãĥ«
    0.06
    wahl
    0.06
    avax
    0.06
    _INITIALIZ
    0.06
    esiz
    0.06
    беÑĢ
    0.06
    Activations Density 0.011%

    No Known Activations