© 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. 3451
    Prev
    Next
    INDEX
    Explanations

    Java-related classes and methods

    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
    ekil
    -0.08
    ÑĥÑĩ
    -0.08
    iotics
    -0.07
    $MESS
    -0.07
    $core
    -0.07
    ÑĥÑĩа
    -0.07
     danmark
    -0.07
    unte
    -0.07
    ELS
    -0.06
    emann
    -0.06
    POSITIVE LOGITS
    ();↵
    0.07
    azer
    0.06
    ski
    0.06
    {};↵
    0.06
    ();
    0.06
    isan
    0.06
    obs
    0.06
    PasswordEncoder
    0.06
    .edu
    0.05
    ian
    0.05
    Activations Density 0.012%

    No Known Activations