© 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. 74975
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions

    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
     اÙĦطب
    -0.07
    erva
    -0.07
    borg
    -0.07
    opi
    -0.07
    uela
    -0.07
    gnu
    -0.07
    اÙģÛĮ
    -0.07
     submar
    -0.07
    erver
    -0.06
    jac
    -0.06
    POSITIVE LOGITS
     halves
    0.08
     half
    0.06
     two
    0.06
    pike
    0.06
    kee
    0.06
     twice
    0.06
    ori
    0.06
     pl
    0.06
    half
    0.05
     midpoint
    0.05
    Activations Density 0.045%

    No Known Activations