© 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. 29263
    Prev
    Next
    INDEX
    Explanations

    terms related to technology leaks and product announcements

    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
    646
    -0.08
     Kaf
    -0.07
    plorer
    -0.07
    SWG
    -0.07
    geme
    -0.07
     آر
    -0.06
    inh
    -0.06
    .FindGameObjectWithTag
    -0.06
    naments
    -0.06
     Ùĩد
    -0.06
    POSITIVE LOGITS
     pre
    0.06
     clock
    0.06
     interesting
    0.06
    ç·
    0.06
    akit
    0.06
     Regulatory
    0.06
    osp
    0.06
     FCC
    0.06
     пок
    0.06
     comprom
    0.06
    Activations Density 0.002%

    No Known Activations