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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. MLP Out
    5. 25-LLAMASCOPE-MLP-131K
    6. 72592
    Prev
    Next
    INDEX
    Explanations

    negative phrases related to action or inaction

    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
    pd
    -0.07
     Ashe
    -0.07
    ãģĮãģĬ
    -0.06
    leon
    -0.06
    rollo
    -0.06
    adlo
    -0.06
    brig
    -0.06
    aç
    -0.06
    ICY
    -0.06
    idge
    -0.06
    POSITIVE LOGITS
    upa
    0.07
    oire
    0.06
    upert
    0.06
    fusion
    0.06
    623
    0.06
    تÙĪ
    0.06
    anton
    0.06
    isoft
    0.06
    ToBounds
    0.06
    ancel
    0.06
    Activations Density 0.038%

    No Known Activations