© 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. 9-LLAMASCOPE-RES-131K
    11. 96563
    Prev
    Next
    INDEX
    Explanations

    references to issues or problems related to coding or programming functions

    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
    edik
    -0.07
    uki
    -0.07
    wie
    -0.06
    wares
    -0.06
    urs
    -0.06
    جات
    -0.06
    олева
    -0.06
    stry
    -0.06
    uzzi
    -0.06
    IX
    -0.06
    POSITIVE LOGITS
    DbType
    0.07
    .assets
    0.07
    afx
    0.07
    anglicky
    0.07
    _MARKER
    0.06
     hã
    0.06
    POCH
    0.06
     Dorm
    0.06
    UBLE
    0.06
     rabbit
    0.06
    Activations Density 0.024%

    No Known Activations