© 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. 15-LLAMASCOPE-RES-131K
    11. 90194
    Prev
    Next
    INDEX
    Explanations

    punctuated statements, primarily related to code or programming syntax

    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
    .loaded
    -0.07
    év
    -0.07
    æĥħ
    -0.07
    äm
    -0.07
    EventManager
    -0.06
    elf
    -0.06
    andler
    -0.06
    GLOSS
    -0.06
    ault
    -0.06
    _TRY
    -0.06
    POSITIVE LOGITS
    uria
    0.06
    472
    0.06
    464
    0.05
     UIScreen
    0.05
    isha
    0.05
    461
    0.05
    大ä¼ļ
    0.05
    ãĤĤãģªãģĦ
    0.05
    arring
    0.05
    net
    0.05
    Activations Density 0.011%

    No Known Activations