© 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. 29927
    Prev
    Next
    INDEX
    Explanations

    classifications or categories related to abilities or experiences

    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
    isset
    -0.06
    ä¸Ŀ
    -0.06
    erialize
    -0.06
    oc
    -0.06
    uw
    -0.06
    owler
    -0.06
    ennie
    -0.06
     throat
    -0.06
    URED
    -0.06
    arias
    -0.06
    POSITIVE LOGITS
     category
    0.18
     Category
    0.15
    category
    0.15
     categories
    0.14
    _category
    0.13
    .category
    0.13
     falls
    0.13
     Categories
    0.13
    -category
    0.13
    Category
    0.12
    Activations Density 0.083%

    No Known Activations