© 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. 86021
    Prev
    Next
    INDEX
    Explanations

    references to authorship and attribution

    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
    .NewReader
    -0.06
    iele
    -0.06
    ippers
    -0.06
    borough
    -0.06
    ManagerInterface
    -0.06
    odor
    -0.06
    lope
    -0.06
    еÑĢÑĤи
    -0.06
    leys
    -0.06
     Dimension
    -0.06
    POSITIVE LOGITS
     reporter
    0.08
     reporters
    0.08
     diseñador
    0.07
    azer
    0.07
    ureau
    0.07
    LOAT
    0.07
     admin
    0.06
    olet
    0.06
     Reported
    0.06
     Fare
    0.06
    Activations Density 0.028%

    No Known Activations