© 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. 73128
    Prev
    Next
    INDEX
    Explanations

    phrases regarding cleaning and maintenance procedures

    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
    engo
    -0.07
    ãĥ³ãĥ
    -0.07
    vic
    -0.07
    enko
    -0.07
    EditMode
    -0.07
    ubble
    -0.06
    owan
    -0.06
     '\''
    -0.06
    öm
    -0.06
    uan
    -0.06
    POSITIVE LOGITS
     needs
    0.09
     wants
    0.07
     wouldn
    0.07
     otherwise
    0.07
     want
    0.07
     need
    0.07
    needs
    0.07
    alles
    0.07
     potÅĻeb
    0.07
     vog
    0.07
    Activations Density 0.043%

    No Known Activations