© 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. 27236
    Prev
    Next
    INDEX
    Explanations

    instructions and tips for mosquito prevention and control

    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
    ustin
    -0.07
     fou
    -0.07
    æĬ¼
    -0.07
    este
    -0.07
    lien
    -0.06
    scal
    -0.06
    _PK
    -0.06
    eyse
    -0.06
    .interfaces
    -0.06
    inode
    -0.06
    POSITIVE LOGITS
     whenever
    0.08
     avoidance
    0.08
     use
    0.07
     Avoid
    0.07
     Limit
    0.07
     avoid
    0.07
    ihu
    0.07
     refrain
    0.07
     limiting
    0.07
     Whenever
    0.06
    Activations Density 0.023%

    No Known Activations