© 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. 38814
    Prev
    Next
    INDEX
    Explanations

    code-related terms associated with synchronization and locking mechanisms

    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
    ukkit
    -0.07
    aeda
    -0.07
    ActionResult
    -0.07
    æĶĿ
    -0.07
    plet
    -0.07
    izi
    -0.07
    arella
    -0.07
    itti
    -0.06
    essler
    -0.06
    anders
    -0.06
    POSITIVE LOGITS
     freeze
    0.08
     IReadOnly
    0.07
    éĿĻ
    0.07
    .ReadOnly
    0.07
     ReadOnly
    0.07
    _READONLY
    0.07
     frozen
    0.06
    snapshot
    0.06
    .snapshot
    0.06
     readOnly
    0.06
    Activations Density 0.002%

    No Known Activations