© 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. 126560
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental regulations and organizational classifications

    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
     bát
    -0.07
     geil
    -0.07
    pane
    -0.07
    ToolStripMenuItem
    -0.07
    culate
    -0.07
    .appspot
    -0.07
    inear
    -0.06
    vala
    -0.06
    zte
    -0.06
    tons
    -0.06
    POSITIVE LOGITS
    -scalable
    0.07
     Marketable
    0.07
    TRL
    0.06
     Constructors
    0.06
    ibox
    0.06
    æĹıèĩªæ²»
    0.06
     Vaugh
    0.06
    aria
    0.06
     Gratuit
    0.06
     Laud
    0.06
    Activations Density 0.085%

    No Known Activations