© 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. 120104
    Prev
    Next
    INDEX
    Explanations

    references to the Spring Framework in programming code

    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
    heet
    -0.07
    noch
    -0.07
    head
    -0.06
    io
    -0.06
    ync
    -0.06
    å±
    -0.06
    ock
    -0.06
    idis
    -0.05
     Yates
    -0.05
    uku
    -0.05
    POSITIVE LOGITS
    .beans
    0.09
    ammers
    0.09
    .stereotype
    0.08
    aje
    0.07
    .lang
    0.07
    GuidId
    0.07
    _Tis
    0.07
    apus
    0.06
    asje
    0.06
    Probe
    0.06
    Activations Density 0.000%

    No Known Activations