© 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. 86078
    Prev
    Next
    INDEX
    Explanations

    references to studies and research findings

    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
    aks
    -0.06
    orm
    -0.06
    iazza
    -0.06
    ìĬ¤íģ¬
    -0.06
     赤
    -0.06
    915
    -0.06
    ucc
    -0.06
    çī¹èī²
    -0.06
    ÑĦи
    -0.06
     Families
    -0.05
    POSITIVE LOGITS
     studies
    0.12
    Studies
    0.09
     Studies
    0.09
    udies
    0.08
     study
    0.07
    .times
    0.07
    oeff
    0.07
     research
    0.07
     studying
    0.07
    à¸ŀà¸ļ
    0.07
    Activations Density 0.012%

    No Known Activations