© 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. 16795
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and data structures

    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
    .IsNullOr
    -0.06
    CursorPosition
    -0.06
    IDER
    -0.06
    itches
    -0.06
     volta
    -0.06
    ieux
    -0.06
    stadt
    -0.06
    بÙĪد
    -0.06
    pz
    -0.06
    atak
    -0.06
    POSITIVE LOGITS
    imet
    0.07
     ç¤
    0.06
    539
    0.06
     calendars
    0.06
    urat
    0.06
    най
    0.06
    ILA
    0.06
    enan
    0.06
     Rare
    0.06
     relent
    0.06
    Activations Density 0.018%

    No Known Activations