© 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. 15-LLAMASCOPE-RES-131K
    11. 87363
    Prev
    Next
    INDEX
    Explanations

    references to machine learning and its improving capabilities

    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
     Linh
    -0.07
     Hoe
    -0.07
    бÑĥдÑĮ
    -0.06
    estr
    -0.06
    slick
    -0.06
    .scalablytyped
    -0.06
    Ðĭ
    -0.06
    .dc
    -0.06
    ÏįÏĢ
    -0.06
     transport
    -0.06
    POSITIVE LOGITS
     accuracy
    0.09
     Accuracy
    0.08
    accuracy
    0.07
     quality
    0.07
    åı¬
    0.07
    ãĥ³ãĥij
    0.07
     ters
    0.06
     algorithm
    0.06
    Accuracy
    0.06
     Settings
    0.06
    Activations Density 0.021%

    No Known Activations