© 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 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. 9-LLAMASCOPE-RES-131K
    11. 97303
    Prev
    Next
    INDEX
    Explanations

    phrases expressing encouragement and appreciation for effort

    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
    enny
    -0.06
    enter
    -0.06
     fest
    -0.06
    elden
    -0.06
    auer
    -0.06
    k
    -0.06
     Kraft
    -0.05
    it
    -0.05
    sez
    -0.05
    xit
    -0.05
    POSITIVE LOGITS
    ossa
    0.08
    ãĥ¼ãĥģ
    0.08
    esson
    0.08
    çĽijåIJ¬é¡µéĿ¢
    0.07
    divid
    0.07
     loin
    0.07
    ettle
    0.07
    PLL
    0.07
    .Rule
    0.07
    piar
    0.07
    Activations Density 0.009%

    No Known Activations