© 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 EvalsExportsinterp-engineNEWAPI 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. 58475
    Prev
    Next
    INDEX
    Explanations

    code-related terms, particularly those associated with file handling and database operations

    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
    iny
    -0.07
    ayi
    -0.07
    dea
    -0.07
    ÑĢоÑĩ
    -0.07
     hâl
    -0.07
    ]âĢı
    -0.07
    arda
    -0.07
    >}'
    -0.07
    ODE
    -0.06
     пеÑĢев
    -0.06
    POSITIVE LOGITS
     thereby
    0.06
     ActionTypes
    0.06
     Reb
    0.06
    ivant
    0.06
    );
    0.06
    ız
    0.06
    opis
    0.06
    807
    0.06
    );↵
    0.06
    enus
    0.05
    Activations Density 0.041%

    No Known Activations