© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 107283
    Prev
    Next
    INDEX
    Explanations

    terms related to events and experiences that convey enjoyment and quality

    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
    cheng
    -0.06
    abei
    -0.06
     tamp
    -0.06
     gridSize
    -0.06
    anca
    -0.06
    anders
    -0.06
    apos
    -0.05
     defining
    -0.05
     Shed
    -0.05
    uet
    -0.05
    POSITIVE LOGITS
     anyone
    0.08
     anybody
    0.08
    สำหร
    0.07
     addition
    0.07
     your
    0.07
     for
    0.07
    IFY
    0.06
    ¤¤
    0.06
    anity
    0.06
     bagi
    0.06
    Activations Density 0.023%

    No Known Activations