© 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 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. 77231
    Prev
    Next
    INDEX
    Explanations

    references to materials and products related to manufacturing and cleaning

    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
     Wag
    -0.06
    psc
    -0.06
    端
    -0.06
    Signature
    -0.06
    åħ¸
    -0.06
    elman
    -0.06
    SharedPointer
    -0.06
    ither
    -0.06
    uthor
    -0.06
    -(
    -0.06
    POSITIVE LOGITS
    .alibaba
    0.08
    .ali
    0.07
    ssql
    0.07
    eps
    0.07
     Alibaba
    0.07
    elong
    0.06
    .mvp
    0.06
    .qual
    0.06
    Ïĥκ
    0.06
    tty
    0.06
    Activations Density 0.029%

    No Known Activations