© 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. 59346
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and web address components

    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
    urgeon
    -0.07
    ych
    -0.06
    ucus
    -0.06
    ugas
    -0.06
    artz
    -0.06
    odka
    -0.06
    etchup
    -0.06
    icensing
    -0.06
    ubs
    -0.06
    leton
    -0.06
    POSITIVE LOGITS
    é¦Ĩ
    0.07
     è±
    0.07
     é¦
    0.07
    /favicon
    0.07
    SystemService
    0.06
     ЦенÑĤÑĢалÑĮ
    0.06
    roid
    0.06
    library
    0.06
    libraries
    0.06
     RMS
    0.06
    Activations Density 0.001%

    No Known Activations