© 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. 106121
    Prev
    Next
    INDEX
    Explanations

    references to characters, plot points, or elements related to mystery and investigation narratives

    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
     seedu
    -0.09
    otts
    -0.08
    ÃĹ↵↵
    -0.08
    adele
    -0.08
    agra
    -0.07
    irection
    -0.07
    .mousePosition
    -0.07
    ãĥ¬ãĥ¼
    -0.07
    asu
    -0.07
     âĨĴ↵↵
    -0.07
    POSITIVE LOGITS
     finally
    0.08
     suddenly
    0.06
     decide
    0.06
     discover
    0.06
     teams
    0.06
     find
    0.06
     convince
    0.06
     discovers
    0.06
     intent
    0.06
     along
    0.06
    Activations Density 0.024%

    No Known Activations