© 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. 28080
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-paced learning and educational flexibility

    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
    oom
    -0.08
    à¸Ľà¸£à¸°à¸ª
    -0.07
    YC
    -0.07
    بع
    -0.07
    askell
    -0.07
    -hook
    -0.06
    ãĥ¼ãĥĬ
    -0.06
    ije
    -0.06
    utomation
    -0.06
    eshire
    -0.06
    POSITIVE LOGITS
     pace
    0.10
     self
    0.07
    pace
    0.07
     Pace
    0.07
     Self
    0.06
    dev
    0.06
     progress
    0.06
    .flex
    0.06
    Self
    0.06
     SELF
    0.06
    Activations Density 0.011%

    No Known Activations