© 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. 17-LLAMASCOPE-RES-131K
    11. 58356
    Prev
    Next
    INDEX
    Explanations

    regulations and legal guidelines related to website access and use

    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
     ìŀĪëĬĶëį°
    -0.07
    ?action
    -0.07
    gem
    -0.07
    ErrorException
    -0.07
    _Context
    -0.07
    INTR
    -0.07
    姫
    -0.07
    viz
    -0.06
     Morm
    -0.06
    iane
    -0.06
    POSITIVE LOGITS
     nor
    0.09
     anymore
    0.08
     unless
    0.07
    apon
    0.07
    unless
    0.07
     anything
    0.06
    deen
    0.06
    .fhir
    0.06
     anywhere
    0.06
     Äijâu
    0.06
    Activations Density 0.001%

    No Known Activations