© 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. 15-LLAMASCOPE-RES-131K
    11. 86800
    Prev
    Next
    INDEX
    Explanations

    structured programming elements in code snippets

    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
    raci
    -0.07
    usercontent
    -0.07
    lease
    -0.06
    erk
    -0.06
    ERC
    -0.06
    reed
    -0.06
     MainAxisAlignment
    -0.06
     sickness
    -0.06
    .IsAny
    -0.06
    Calibri
    -0.06
    POSITIVE LOGITS
    kest
    0.07
    (æľĪ
    0.06
     vale
    0.06
     Dorm
    0.06
    FW
    0.06
    è¼Ŀ
    0.06
    avid
    0.06
    avan
    0.06
    anga
    0.06
     EÅŁ
    0.06
    Activations Density 0.008%

    No Known Activations