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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 61547
    Prev
    Next
    INDEX
    Explanations

    references to testing frameworks and test cases in code

    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
    sti
    -0.06
    itt
    -0.06
     fet
    -0.06
    inds
    -0.06
    atr
    -0.06
    424
    -0.06
     Neck
    -0.06
    ETY
    -0.06
    ekil
    -0.06
     ÙħØ«
    -0.06
    POSITIVE LOGITS
    ê·¹
    0.07
    _framework
    0.07
    .TestCase
    0.06
    .getStyle
    0.06
    SED
    0.06
    olate
    0.06
     Coupon
    0.06
    mando
    0.06
    ZERO
    0.06
    çķªåı·
    0.06
    Activations Density 0.000%

    No Known Activations