© 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. 31205
    Prev
    Next
    INDEX
    Explanations

    phrases related to singular or unique occurrences

    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
    .vertx
    -0.07
    CrLf
    -0.07
    ando
    -0.06
    ardi
    -0.06
    metis
    -0.06
    atur
    -0.06
    озÑĸ
    -0.06
    arda
    -0.06
    agnosis
    -0.06
    fac
    -0.06
    POSITIVE LOGITS
     once
    0.22
    once
    0.19
     Once
    0.18
    ä¸Ģ次
    0.18
    Once
    0.18
    _once
    0.17
    .once
    0.14
     Ùħرة
    0.14
     einmal
    0.13
    _ONCE
    0.13
    Activations Density 0.068%

    No Known Activations