© 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. 69773
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of enhancement or improvement

    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
    stanov
    -0.07
    afen
    -0.07
    TREE
    -0.07
    AXB
    -0.07
     inFile
    -0.07
    á»ķi
    -0.07
    anzi
    -0.07
    272
    -0.07
    orpor
    -0.06
    ãģĿãģĹãģ¦
    -0.06
    POSITIVE LOGITS
     nor
    0.10
    acker
    0.09
    akin
    0.07
     or
    0.06
    Than
    0.06
    oop
    0.06
    nor
    0.06
    _blueprint
    0.06
    elden
    0.06
     Millennium
    0.06
    Activations Density 0.008%

    No Known Activations