© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88281
    Prev
    Next
    INDEX
    Explanations

    references to Java programming language components and their classes

    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
    ady
    -0.07
    eb
    -0.07
    dra
    -0.07
    olumn
    -0.07
     Semi
    -0.07
    ife
    -0.07
    ogan
    -0.07
    typedef
    -0.07
    llum
    -0.07
    ory
    -0.06
    POSITIVE LOGITS
    UTERS
    0.07
     Rarity
    0.06
    olis
    0.06
     sil
    0.06
    /Object
    0.06
    iaux
    0.06
    ugins
    0.06
     gross
    0.06
    rut
    0.05
     absentee
    0.05
    Activations Density 0.001%

    No Known Activations