© 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. 29079
    Prev
    Next
    INDEX
    Explanations

    references to methods and properties related to programming constructs

    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
    ulia
    -0.07
    -0.06
     Harmony
    -0.06
    (s
    -0.06
     forth
    -0.05
    immel
    -0.05
    onet
    -0.05
    ichte
    -0.05
    ijd
    -0.05
    rams
    -0.05
    POSITIVE LOGITS
    odash
    0.07
    FORCE
    0.07
    568
    0.07
    ÑĥкÑĤ
    0.07
    tah
    0.06
     itself
    0.06
    ¹Ħ
    0.06
    divid
    0.06
    uku
    0.06
    -cols
    0.06
    Activations Density 0.128%

    No Known Activations