© 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. 17-LLAMASCOPE-RES-131K
    11. 4167
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of revealing or disclosing information

    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
    -corner
    -0.07
    gaard
    -0.07
    ãĥĸãĥ«
    -0.07
    лаз
    -0.07
    ìĮ
    -0.07
    pee
    -0.06
    ãĥ©ãĤ¹
    -0.06
    clr
    -0.06
     ellipse
    -0.06
    corner
    -0.06
    POSITIVE LOGITS
     desn
    0.07
    uten
    0.06
     eff
    0.06
    ML
    0.06
     ICC
    0.06
    á»Ńa
    0.06
    eve
    0.06
     ÙĨÙĪÙģ
    0.06
     Siz
    0.06
     uncert
    0.06
    Activations Density 0.001%

    No Known Activations