© 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. 14781
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations or initiatives related to clean water and sanitation

    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
     Bale
    -0.07
    etten
    -0.06
    sgiving
    -0.06
    dee
    -0.06
    holm
    -0.06
    ALLERY
    -0.06
    LoggedIn
    -0.06
    utter
    -0.06
     Dudley
    -0.06
    adel
    -0.06
    POSITIVE LOGITS
    by
    0.13
    Posted
    0.11
     Posted
    0.11
    admin
    0.08
     posted
    0.08
    ala
    0.07
    posted
    0.07
    ulace
    0.07
    egt
    0.06
    ker
    0.06
    Activations Density 0.099%

    No Known Activations