© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 83329
    Prev
    Next
    INDEX
    Explanations

    questions about important concepts and their significance

    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
    olla
    -0.06
     whole
    -0.06
    oller
    -0.06
     consolation
    -0.06
    ero
    -0.06
     particular
    -0.05
     carte
    -0.05
     session
    -0.05
     Gothic
    -0.05
     roadside
    -0.05
    POSITIVE LOGITS
    bjerg
    0.08
     electr
    0.07
    ¿
    0.07
     withObject
    0.07
    vak
    0.07
    akk
    0.07
    asant
    0.07
     forCellReuseIdentifier
    0.07
    ikit
    0.07
    оÑģоб
    0.07
    Activations Density 0.005%

    No Known Activations