© 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. 131003
    Prev
    Next
    INDEX
    Explanations

    statements suggesting requirements or conditions for actions

    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
     sometimes
    -0.07
    æIJŃ
    -0.06
     ((((
    -0.06
    ãĥ¼ãĥª
    -0.06
     Consortium
    -0.06
    ools
    -0.06
     Lanc
    -0.06
     Sometimes
    -0.06
     Tak
    -0.06
    chts
    -0.06
    POSITIVE LOGITS
     future
    0.08
    ãĤĤãģ£ãģ¨
    0.08
    ancode
    0.08
    Eventually
    0.08
     бÑĥдÑĥÑī
    0.07
    -нибÑĥдÑĮ
    0.07
    lun
    0.07
    alars
    0.07
    oor
    0.07
    borg
    0.07
    Activations Density 0.024%

    No Known Activations