© 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. 26486
    Prev
    Next
    INDEX
    Explanations

    references to events, particularly fundraisers and galas

    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
     Bik
    -0.06
     extra
    -0.06
     hom
    -0.06
     self
    -0.06
     run
    -0.05
    .extra
    -0.05
     w
    -0.05
    io
    -0.05
     free
    -0.05
     budget
    -0.05
    POSITIVE LOGITS
     ******************************************************************************↵
    0.08
    ernals
    0.08
    анÑĮ
    0.07
     kabil
    0.07
    onus
    0.07
    ÙĪÛĮد
    0.07
    ::$
    0.07
    APE
    0.07
     ì¤Ģ
    0.07
    ugar
    0.07
    Activations Density 0.021%

    No Known Activations