© 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. 15-LLAMASCOPE-RES-131K
    11. 458
    Prev
    Next
    INDEX
    Explanations

    Java-related exceptions in programming contexts

    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
    tons
    -0.07
    fé
    -0.06
     ninh
    -0.06
    acco
    -0.06
    zept
    -0.06
    ogie
    -0.06
    seau
    -0.06
    änner
    -0.06
    bserv
    -0.06
    prit
    -0.06
    POSITIVE LOGITS
    oldt
    0.07
    alice
    0.07
    harma
    0.06
    OTA
    0.06
    ãĥ³ãĥĪ
    0.06
    erville
    0.06
    alf
    0.06
    ike
    0.06
     Westbrook
    0.06
    éĿĴ
    0.06
    Activations Density 0.003%

    No Known Activations