© 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. 9-LLAMASCOPE-RES-131K
    11. 95157
    Prev
    Next
    INDEX
    Explanations

    terminology related to commutativity and algebraic structures

    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
    krv
    -0.07
    ftime
    -0.07
    ein
    -0.07
    vyk
    -0.07
    onte
    -0.07
    리카
    -0.07
    idis
    -0.07
    UTTON
    -0.07
    TOTYPE
    -0.07
    pus
    -0.07
    POSITIVE LOGITS
    abbage
    0.06
    96
    0.06
    resh
    0.06
     Nat
    0.06
    Tak
    0.06
    son
    0.06
    ãĥ³ãĥĩ
    0.06
     Tak
    0.05
    608
    0.05
    321
    0.05
    Activations Density 0.009%

    No Known Activations