© 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. 80455
    Prev
    Next
    INDEX
    Explanations

    sensory experiences and descriptions related to smells and tastes

    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
     Independence
    -0.07
     independence
    -0.07
     regional
    -0.06
     Rah
    -0.06
     inject
    -0.06
     Regional
    -0.06
     pace
    -0.05
    Independ
    -0.05
     GOT
    -0.05
     Rec
    -0.05
    POSITIVE LOGITS
     aroma
    0.14
     запаÑħ
    0.13
    é¦Ļ
    0.11
     fragrance
    0.11
     smell
    0.11
     scent
    0.11
     arom
    0.11
     аÑĢом
    0.10
     smells
    0.10
     smelled
    0.10
    Activations Density 0.029%

    No Known Activations