© 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. 28965
    Prev
    Next
    INDEX
    Explanations

    phrases related to product availability and options

    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
     Specialist
    -0.06
    rias
    -0.06
    ey
    -0.06
    iales
    -0.05
    yar
    -0.05
    UIL
    -0.05
     until
    -0.05
    ansa
    -0.05
     and
    -0.05
     Coun
    -0.05
    POSITIVE LOGITS
     seçenek
    0.07
     $?
    0.07
    .synthetic
    0.07
    Interop
    0.07
    )>>
    0.07
    سط
    0.07
    Ñĸйно
    0.07
    options
    0.07
     strftime
    0.07
    ÑĸÑĪ
    0.07
    Activations Density 0.003%

    No Known Activations