© 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. 15258
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations and guidelines

    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
     another
    -0.09
    another
    -0.07
     Another
    -0.07
    TransparentColor
    -0.07
    anson
    -0.07
    Another
    -0.06
     ActionTypes
    -0.06
    åı¦ä¸Ģ
    -0.06
    oyer
    -0.06
    loom
    -0.06
    POSITIVE LOGITS
    GENERAL
    0.10
    general
    0.10
     general
    0.09
    ìĿ¼ë°ĺ
    0.09
    _general
    0.09
    ìłĢ
    0.09
     æĻ®éĢļ
    0.09
    ä¸ĢèĪ¬
    0.09
     général
    0.08
     normal
    0.08
    Activations Density 0.071%

    No Known Activations