© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29817
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and properties related to sets and inequalities

    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
    onto
    -0.07
    icont
    -0.07
    agar
    -0.06
    abi
    -0.06
    mdb
    -0.06
    uru
    -0.06
    uation
    -0.06
    outer
    -0.06
    nee
    -0.06
    uran
    -0.06
    POSITIVE LOGITS
    ť
    0.08
    ushman
    0.07
    isque
    0.07
    CastException
    0.07
    qué
    0.07
    ckt
    0.07
    (Method
    0.07
    checkout
    0.07
    CAC
    0.07
    .Magenta
    0.06
    Activations Density 0.075%

    No Known Activations