© 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. 85875
    Prev
    Next
    INDEX
    Explanations

    technical language related to AI and machine learning methodologies

    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
     bay
    -0.07
    revolution
    -0.07
    CCR
    -0.07
    geist
    -0.06
     overrun
    -0.06
     Sele
    -0.06
    enu
    -0.06
    सर
    -0.06
    ÑĢеÑĪ
    -0.06
    PropertyValue
    -0.06
    POSITIVE LOGITS
    uer
    0.07
     knowledge
    0.07
    nowledge
    0.07
    autiful
    0.07
     Knowledge
    0.07
    Looper
    0.06
    isser
    0.06
    knowledge
    0.06
     explicitly
    0.06
     manual
    0.06
    Activations Density 0.062%

    No Known Activations