© 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. 126726
    Prev
    Next
    INDEX
    Explanations

    identifiers and associated metadata in a structured data format

    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
    ohana
    -0.07
    ohl
    -0.07
    URLException
    -0.07
     LGPL
    -0.07
    BuilderInterface
    -0.07
    enegro
    -0.07
    ervas
    -0.06
    uze
    -0.06
    ultureInfo
    -0.06
    ManagerInterface
    -0.06
    POSITIVE LOGITS
    ocs
    0.07
    [rand
    0.06
    EMS
    0.06
    ạt
    0.06
     varchar
    0.06
    DataGridViewTextBoxColumn
    0.06
    nullable
    0.06
     type
    0.06
     Sultan
    0.06
    оÑĤÑĮ
    0.05
    Activations Density 0.045%

    No Known Activations