© 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. 56078
    Prev
    Next
    INDEX
    Explanations

    architectural and design-related terms

    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
     "
    -0.06
    248
    -0.05
     Coun
    -0.05
     United
    -0.05
    469
    -0.05
     million
    -0.05
    acos
    -0.05
     &
    -0.05
    Fo
    -0.05
    enberg
    -0.05
    POSITIVE LOGITS
    unsch
    0.09
    ãĢ
    0.08
    datable
    0.07
    mada
    0.07
    WEEN
    0.07
    äºĮ人
    0.07
    .sax
    0.07
    SError
    0.07
    ÑĩаÑĤ
    0.07
    apy
    0.07
    Activations Density 0.003%

    No Known Activations