© 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. 27951
    Prev
    Next
    INDEX
    Explanations

    specific numerical codes or publication years in academic or scientific contexts

    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
    éĻµ
    -0.07
    amil
    -0.07
    ivet
    -0.07
    reur
    -0.07
    ocities
    -0.07
    enson
    -0.07
    ibur
    -0.06
    浪
    -0.06
     NSRange
    -0.06
    ToDevice
    -0.06
    POSITIVE LOGITS
    eview
    0.06
    BAT
    0.06
    uar
    0.05
     vig
    0.05
    Ins
    0.05
     Garn
    0.05
    /Gate
    0.05
    fried
    0.05
     Cone
    0.05
    /target
    0.05
    Activations Density 0.001%

    No Known Activations