© 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. 9-LLAMASCOPE-RES-131K
    11. 97079
    Prev
    Next
    INDEX
    Explanations

    programming syntax, particularly related to boolean expressions and logical conditions

    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
    /GPL
    -0.08
    ..↵↵↵↵
    -0.07
     volunte
    -0.07
    ITTE
    -0.07
     giác
    -0.07
    gaard
    -0.07
    _fixture
    -0.07
    itele
    -0.07
    xBD
    -0.07
    .viewDidLoad
    -0.07
    POSITIVE LOGITS
    ByPrimaryKey
    0.06
    hos
    0.06
    krit
    0.06
    SA
    0.06
    CA
    0.06
     Sure
    0.06
    بات
    0.05
    Âł
    0.05
     Bonnie
    0.05
     etc
    0.05
    Activations Density 0.019%

    No Known Activations