© 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. 117118
    Prev
    Next
    INDEX
    Explanations

    programming or coding constructs related to session management

    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
    heit
    -0.07
     ngừng
    -0.07
     recep
    -0.07
    ADX
    -0.07
    RecognitionException
    -0.07
    .CreateIndex
    -0.07
    hole
    -0.07
    ANGED
    -0.06
    rise
    -0.06
    Į¨
    -0.06
    POSITIVE LOGITS
     session
    0.12
     Session
    0.10
    -session
    0.10
     sessions
    0.10
    /session
    0.10
    SESSION
    0.09
    session
    0.09
    Session
    0.08
     Sessions
    0.08
     SESSION
    0.08
    Activations Density 0.012%

    No Known Activations