© 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. 69606
    Prev
    Next
    INDEX
    Explanations

    references to online platforms for music promotion and crowdfunding

    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
    ÂŃ
    -0.06
    hints
    -0.06
    Ìģ
    -0.05
    âĢį
    -0.05
    âĢIJ
    -0.05
    -v
    -0.05
    -for
    -0.05
    ÃŃÅĻ
    -0.05
    resultCode
    -0.05
     toy
    -0.05
    POSITIVE LOGITS
    olio
    0.08
    ConfigurationException
    0.07
    lein
    0.07
    urdy
    0.07
    untime
    0.07
     ê²ģ
    0.07
    à¤ľà¤¹
    0.07
    leyin
    0.07
    modifiable
    0.07
    ë§ģ
    0.07
    Activations Density 0.029%

    No Known Activations