© 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. 26979
    Prev
    Next
    INDEX
    Explanations

    references to complexity and the multifaceted nature of subjects

    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
    uforia
    -0.07
    mpr
    -0.07
    inx
    -0.07
    arius
    -0.07
     ---------------------------------------------------------------------------↵
    -0.07
    eut
    -0.07
    istik
    -0.07
    Ø«ÛĮر
    -0.07
    ji
    -0.07
    398
    -0.07
    POSITIVE LOGITS
     glory
    0.07
     its
    0.07
    eni
    0.06
    ipa
    0.06
     glorious
    0.06
     diversity
    0.06
    .aspect
    0.06
     ex
    0.06
    CB
    0.06
     Second
    0.05
    Activations Density 0.004%

    No Known Activations