© 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. 72109
    Prev
    Next
    INDEX
    Explanations

    key performance indicators and financial metrics

    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
    ilan
    -0.07
     resultant
    -0.07
    æĿŁ
    -0.06
     å¹³
    -0.06
     Khoa
    -0.06
    Statics
    -0.06
     possessing
    -0.06
     shell
    -0.06
    emoc
    -0.06
     ÑĦакÑĤ
    -0.06
    POSITIVE LOGITS
     Invent
    0.07
    409
    0.07
     Theater
    0.07
    öh
    0.06
     mies
    0.06
    oso
    0.06
    Aceptar
    0.06
     everybody
    0.06
    askell
    0.06
     Instruments
    0.06
    Activations Density 0.000%

    No Known Activations