© 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. 76441
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and patterns associated with caching and configuration parameters

    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
    ÑĪÑĤ
    -0.07
    iche
    -0.07
    iance
    -0.06
    elles
    -0.06
    ì²Ļ
    -0.06
    761
    -0.06
     ju
    -0.06
    isposable
    -0.06
    ">ÃĹ</
    -0.06
    ween
    -0.06
    POSITIVE LOGITS
     enabled
    0.08
    roke
    0.07
     enable
    0.06
     Enable
    0.06
     strategy
    0.06
    iple
    0.06
    Enabled
    0.06
     allowed
    0.06
    enabled
    0.06
    MaxLength
    0.06
    Activations Density 0.150%

    No Known Activations