© 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 EvalsExportsAPI 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. 61033
    Prev
    Next
    INDEX
    Explanations

    references to food ingredients and preparation methods

    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
    ̧
    -0.07
    odem
    -0.07
    ijke
    -0.07
     mastur
    -0.07
    .FindGameObjectWithTag
    -0.07
    пÑĢа
    -0.07
    /misc
    -0.07
    incare
    -0.07
    inç
    -0.07
     incel
    -0.07
    POSITIVE LOGITS
     another
    0.07
     similarly
    0.07
    ãģĵãģ¡ãĤī
    0.07
     equally
    0.07
     ebenfalls
    0.07
    another
    0.06
    (s
    0.06
     separately
    0.06
     Willis
    0.06
     اÙĦأخرÙī
    0.06
    Activations Density 0.403%

    No Known Activations