© 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. 73254
    Prev
    Next
    INDEX
    Explanations

    phrases indicating adequacy or sufficiency

    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
    bing
    -0.07
    olph
    -0.07
    shelf
    -0.07
    jl
    -0.06
    lines
    -0.06
     frais
    -0.06
     thù
    -0.06
    ÃŁer
    -0.06
     laten
    -0.06
    pery
    -0.06
    POSITIVE LOGITS
    ender
    0.07
    auce
    0.07
    arian
    0.07
     enough
    0.07
    JUnit
    0.06
    /full
    0.06
    lessly
    0.06
    ledged
    0.06
    iente
    0.06
    ych
    0.06
    Activations Density 0.019%

    No Known Activations