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. 5063
    Prev
    Next
    INDEX
    Explanations

    geographic locations and their associated events or activities

    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
    DSL
    -0.07
    ROL
    -0.07
    itis
    -0.06
    yas
    -0.06
    -css
    -0.06
     Glover
    -0.06
    ]int
    -0.06
    issa
    -0.06
    neau
    -0.06
    ãģĬãĤĬ
    -0.06
    POSITIVE LOGITS
    uc
    0.06
    交
    0.06
     Airways
    0.06
    é¾Ħ
    0.06
     benches
    0.06
    İ
    0.06
    slots
    0.06
    ieder
    0.06
    tern
    0.06
    ella
    0.06
    Activations Density 0.003%

    No Known Activations