© 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. 15-LLAMASCOPE-RES-131K
    11. 87968
    Prev
    Next
    INDEX
    Explanations

    descriptive elements related to architecture and historical materials

    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
    evi
    -0.06
    ÑĢÑĸд
    -0.06
     GarcÃŃa
    -0.06
     marg
    -0.06
     Assertion
    -0.06
     Brass
    -0.06
    ìĬµ
    -0.06
    otron
    -0.06
     developed
    -0.05
     brass
    -0.05
    POSITIVE LOGITS
    loff
    0.08
    PCA
    0.07
    ãĢĤãĢĤ↵↵
    0.07
     quar
    0.07
    Reserved
    0.07
    .quote
    0.07
    usercontent
    0.06
    ussy
    0.06
     building
    0.06
    Rejected
    0.06
    Activations Density 0.010%

    No Known Activations