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. 72556
    Prev
    Next
    INDEX
    Explanations

    references to ongoing conflicts and issues related to territorial disputes

    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
     peace
    -0.15
     Peace
    -0.15
    Peace
    -0.15
    peace
    -0.13
     миÑĢ
    -0.08
     civil
    -0.07
     pe
    -0.07
    treeview
    -0.07
     pac
    -0.07
    /package
    -0.07
    POSITIVE LOGITS
    rary
    0.07
    á»ģ
    0.07
    @Web
    0.07
     ed
    0.06
     dem
    0.06
    ietet
    0.06
    vale
    0.06
    uales
    0.06
    edd
    0.06
    fight
    0.06
    Activations Density 0.227%

    No Known Activations