© 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. 81116
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or considerations in decision-making

    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
    iaz
    -0.08
    enberg
    -0.07
    émon
    -0.07
    orgen
    -0.07
    adow
    -0.06
    978
    -0.06
    errick
    -0.06
    adil
    -0.06
    getRequest
    -0.06
     Clifford
    -0.06
    POSITIVE LOGITS
    Ñľ
    0.07
    etto
    0.06
    388
    0.06
     arter
    0.06
    ewan
    0.06
    ê°¤
    0.06
    stal
    0.06
    lü
    0.06
    гл
    0.06
     Sheldon
    0.06
    Activations Density 0.001%

    No Known Activations