© 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 EvalsExportsinterp-engineNEWAPI 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. 93225
    Prev
    Next
    INDEX
    Explanations

    references to historical or political entities and structures

    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
    -0.07
    ponde
    -0.07
    odiac
    -0.07
    ož
    -0.07
    à¸ŀย
    -0.07
    emmel
    -0.06
    živ
    -0.06
    olet
    -0.06
    ktor
    -0.06
    anut
    -0.06
    POSITIVE LOGITS
    _alarm
    0.07
    semblies
    0.06
    oper
    0.06
     Soviets
    0.06
     absentee
    0.06
     Soviet
    0.06
     socially
    0.06
    é®
    0.06
    oe
    0.06
    -addons
    0.06
    Activations Density 0.003%

    No Known Activations