© 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. 55217
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to financial figures or economic conditions

    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
    piry
    -0.07
    ToLocal
    -0.07
    ãĥªãĥ¼ãĤº
    -0.06
    959
    -0.06
     cort
    -0.06
    icy
    -0.06
    vens
    -0.06
    oya
    -0.06
    ivi
    -0.06
    hol
    -0.06
    POSITIVE LOGITS
    egt
    0.07
    бÑĢÑı
    0.07
    uche
    0.07
     Views
    0.06
    LOB
    0.06
    kaz
    0.06
    ÑĢим
    0.06
    incer
    0.06
     Employer
    0.06
     ""},↵
    0.06
    Activations Density 0.001%

    No Known Activations