© 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. 17-LLAMASCOPE-RES-131K
    11. 3483
    Prev
    Next
    INDEX
    Explanations

    references to specific technology products and companies

    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
    .null
    -0.07
    imei
    -0.07
    \Framework
    -0.06
     Xperia
    -0.06
    .travel
    -0.06
     STDERR
    -0.06
    æ¿ĥ
    -0.06
    änn
    -0.06
     fieldType
    -0.06
    INUX
    -0.06
    POSITIVE LOGITS
    cie
    0.08
    ibling
    0.07
     Perf
    0.07
     Mant
    0.06
    etim
    0.06
     Kendall
    0.06
     VA
    0.06
    ARB
    0.06
    elper
    0.06
     card
    0.06
    Activations Density 0.004%

    No Known Activations