© 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. 17-LLAMASCOPE-RES-131K
    11. 117327
    Prev
    Next
    INDEX
    Explanations

    references to specific events or items related to conferences and vehicles

    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
    .xmlbeans
    -0.08
     pár
    -0.07
     spou
    -0.07
     restau
    -0.07
    ldr
    -0.07
     nackte
    -0.06
    rella
    -0.06
     giá»Ŀ
    -0.06
    byt
    -0.06
     meiden
    -0.06
    POSITIVE LOGITS
    RootElement
    0.07
    aks
    0.07
     Caucus
    0.06
    ube
    0.06
     flick
    0.06
    ouble
    0.05
    821
    0.05
    idak
    0.05
    afx
    0.05
    alach
    0.05
    Activations Density 0.000%

    No Known Activations