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. 72604
    Prev
    Next
    INDEX
    Explanations

    geographic location identifiers, particularly states and postal codes

    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
    eprom
    -0.07
    Congress
    -0.07
    stro
    -0.07
    InThe
    -0.06
    .archive
    -0.06
    hower
    -0.06
     kred
    -0.06
    onym
    -0.06
    orning
    -0.06
    .GroupLayout
    -0.06
    POSITIVE LOGITS
    nik
    0.07
     val
    0.06
     bas
    0.06
     Dez
    0.06
    -enabled
    0.06
    inz
    0.06
    duplicate
    0.06
     tr
    0.06
     Cort
    0.06
     Universal
    0.05
    Activations Density 0.003%

    No Known Activations