© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95400
    Prev
    Next
    INDEX
    Explanations

    references to various types of courses or race tracks

    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
    ãĥ©ãĥ³ãĥī
    -0.07
     ÐĿÑĸ
    -0.07
    lander
    -0.07
     dado
    -0.06
    apos
    -0.06
    iana
    -0.06
    anse
    -0.06
    iddleware
    -0.06
    VERTISE
    -0.06
    ÑĤеÑĢи
    -0.06
    POSITIVE LOGITS
    eya
    0.07
    parm
    0.06
    bla
    0.06
    executor
    0.06
    bru
    0.06
    pow
    0.06
     path
    0.06
     Path
    0.06
     genitals
    0.06
    totals
    0.05
    Activations Density 0.010%

    No Known Activations