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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126936
    Prev
    Next
    INDEX
    Explanations

    specific lines of code or error messages in Java programming

    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
    czy
    -0.07
    ercul
    -0.07
    еÑĪ
    -0.07
    591
    -0.06
    2
    -0.06
    891
    -0.06
     диви
    -0.06
    iê
    -0.06
    chwitz
    -0.06
    abis
    -0.06
    POSITIVE LOGITS
     porr
    0.07
    unga
    0.07
    ÃĹ↵↵
    0.06
     Ä°z
    0.06
    Gro
    0.06
     Injector
    0.06
     sir
    0.06
    ãĥ£
    0.06
    hin
    0.06
    AccessException
    0.06
    Activations Density 0.006%

    No Known Activations