© 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. 15-LLAMASCOPE-RES-131K
    11. 27593
    Prev
    Next
    INDEX
    Explanations

    references to funding sources and financial support for research

    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
    -indent
    -0.08
    recht
    -0.08
    ละ
    -0.08
    PCS
    -0.07
    νια
    -0.07
    DataExchange
    -0.07
    .Interop
    -0.07
     DISPATCH
    -0.07
    CellStyle
    -0.07
    udeau
    -0.07
    POSITIVE LOGITS
     frozen
    0.07
     Exact
    0.06
    lg
    0.06
     grant
    0.06
    ooth
    0.06
     unp
    0.05
     support
    0.05
    encion
    0.05
     Dorm
    0.05
    umb
    0.05
    Activations Density 0.017%

    No Known Activations