© 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. 4674
    Prev
    Next
    INDEX
    Explanations

    activities related to artistic creation and trade

    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
     distributors
    -0.06
    uat
    -0.06
    ksiyon
    -0.06
    овеÑĢ
    -0.06
    enting
    -0.06
     yesterday
    -0.06
     manufacturers
    -0.06
     registrations
    -0.05
    vla
    -0.05
    _DX
    -0.05
    POSITIVE LOGITS
     commissioned
    0.08
    cene
    0.08
     UIGraphics
    0.08
     requester
    0.07
    ScreenState
    0.07
     êµ
    0.07
    deadline
    0.07
    Deadline
    0.07
     stret
    0.07
    (dead
    0.07
    Activations Density 0.002%

    No Known Activations