© 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. 118678
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal accreditation and qualifications

    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
    unkt
    -0.08
     Weekly
    -0.07
    unar
    -0.07
    elib
    -0.07
    Weekly
    -0.07
    oit
    -0.06
    CTX
    -0.06
    ym
    -0.06
    peria
    -0.06
    .sul
    -0.06
    POSITIVE LOGITS
    /board
    0.07
    оваÑĢи
    0.06
     Specialty
    0.06
     Fellow
    0.06
     Rav
    0.06
     Board
    0.06
     exam
    0.06
     Society
    0.06
     specialty
    0.06
    γι
    0.05
    Activations Density 0.005%

    No Known Activations