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. 72557
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Dodge."

    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
    deaux
    -0.06
    ÏĦÏģι
    -0.06
    peria
    -0.06
    abi
    -0.06
    -console
    -0.06
    isc
    -0.06
     ern
    -0.06
     pe
    -0.06
    oured
    -0.06
    .Fixed
    -0.06
    POSITIVE LOGITS
    ivan
    0.07
    ARAM
    0.07
    ILED
    0.07
     Metropolitan
    0.06
    ullo
    0.06
     Strait
    0.06
    Ĵáŀ
    0.06
    ê°ģ
    0.06
    _visited
    0.06
    iven
    0.06
    Activations Density 0.002%

    No Known Activations