© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 29071
    Prev
    Next
    INDEX
    Explanations

    references to freedom of speech and constitutional rights

    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
    ec
    -0.07
    ify
    -0.06
     --------------------------------------------------------------------------↵
    -0.06
    çĢ¬
    -0.06
    .tie
    -0.06
     Commod
    -0.05
    itzer
    -0.05
    âĢ¦↵
    -0.05
    733
    -0.05
    isko
    -0.05
    POSITIVE LOGITS
    ¬´
    0.07
    uento
    0.07
    Ħĸ
    0.07
    ãĥ¼ãĥĬ
    0.07
    elas
    0.07
     protections
    0.07
    _ios
    0.07
     centuries
    0.07
    kaar
    0.07
    iyat
    0.07
    Activations Density 0.020%

    No Known Activations