© 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. 14571
    Prev
    Next
    INDEX
    Explanations

    medical conditions and their associated risks or side effects

    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
    OUSE
    -0.08
    celik
    -0.07
    Normals
    -0.07
    ãĥ©ãĤ¤ãĥĪ
    -0.07
    ÙĪزÙĩ
    -0.07
    éĽ
    -0.07
    isas
    -0.07
    æľĭ
    -0.07
    agem
    -0.07
    okud
    -0.07
    POSITIVE LOGITS
     reported
    0.07
     association
    0.07
    otal
    0.07
    ota
    0.06
    rey
    0.06
     associations
    0.06
    je
    0.06
     reports
    0.06
    782
    0.06
    association
    0.06
    Activations Density 0.005%

    No Known Activations