© 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. 2898
    Prev
    Next
    INDEX
    Explanations

    distinct names and references within a structured context

    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
    ków
    -0.05
    /entities
    -0.05
    -sdk
    -0.05
    ,,,,,,,,
    -0.05
     tendency
    -0.05
    áy
    -0.05
     paginate
    -0.05
    åĮ
    -0.05
     authorize
    -0.05
     Ñģоз
    -0.05
    POSITIVE LOGITS
    oulos
    0.08
    itsu
    0.08
    gio
    0.08
    anja
    0.07
    urv
    0.07
    Link
    0.07
    eyh
    0.07
    ervo
    0.07
    .cent
    0.07
    inkel
    0.07
    Activations Density 0.023%

    No Known Activations