© 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. 105960
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to database functionalities, specifically focusing on SQLite interactions

    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
    akra
    -0.08
    ifo
    -0.07
    pton
    -0.06
    asurer
    -0.06
    ucene
    -0.06
    ripp
    -0.06
     localVar
    -0.06
    heck
    -0.06
     filtr
    -0.05
     minOccurs
    -0.05
    POSITIVE LOGITS
    ë£Į
    0.07
    æ·»
    0.07
     Pierre
    0.06
     Macros
    0.06
    ç´
    0.06
     IntPtr
    0.06
    Macro
    0.06
    èŁ
    0.06
    òng
    0.06
    ãĥ³ãĥĩ
    0.06
    Activations Density 0.040%

    No Known Activations