© 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. 62645
    Prev
    Next
    INDEX
    Explanations

    references to examples and uses of various products or methods

    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
    моÑģ
    -0.07
    ãĤ´ãĥª
    -0.07
    zem
    -0.07
    жÑĥ
    -0.07
    raphics
    -0.07
    bish
    -0.07
    venge
    -0.07
     нÑĸколи
    -0.06
    :animated
    -0.06
    ãĥ©ãĤ¤ãĥ³
    -0.06
    POSITIVE LOGITS
     uses
    0.10
     used
    0.10
     use
    0.10
     applications
    0.09
     Uses
    0.08
     Used
    0.08
     Applications
    0.08
    çĶ¨äºİ
    0.08
    uses
    0.08
    Used
    0.08
    Activations Density 0.059%

    No Known Activations