© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88098
    Prev
    Next
    INDEX
    Explanations

    culinary terms and cooking processes

    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
    enity
    -0.07
    imen
    -0.07
     diluted
    -0.07
    Composition
    -0.06
    egot
    -0.06
    _PROTO
    -0.06
     опеÑĢ
    -0.06
    ensis
    -0.06
    enario
    -0.06
     nipple
    -0.06
    POSITIVE LOGITS
    ostel
    0.08
    ãĥ¬ãĥĥãĥĪ
    0.07
    ometers
    0.07
     sugars
    0.06
     sweetness
    0.06
     Venus
    0.06
     sweet
    0.06
    jon
    0.06
    uste
    0.06
    aille
    0.06
    Activations Density 0.023%

    No Known Activations