© 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. 125641
    Prev
    Next
    INDEX
    Explanations

    elements related to contextual understanding in applications and studies

    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
    лада
    -0.06
    atten
    -0.06
     zn
    -0.06
     kıs
    -0.06
    ocket
    -0.06
    bild
    -0.06
    ox
    -0.06
    ertz
    -0.06
     æŀ
    -0.05
     Trou
    -0.05
    POSITIVE LOGITS
     real
    0.12
     actual
    0.11
    -real
    0.10
    actual
    0.10
     Actual
    0.10
    (real
    0.10
    Actual
    0.10
     realistic
    0.09
     environment
    0.09
     realism
    0.09
    Activations Density 0.018%

    No Known Activations