© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56043
    Prev
    Next
    INDEX
    Explanations

    references to "Hamilton" and its variants

    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
    aug
    -0.07
    IME
    -0.06
    ihu
    -0.06
    anut
    -0.06
    owl
    -0.06
    TEE
    -0.06
    gis
    -0.06
     Trib
    -0.06
    _MALLOC
    -0.06
    744
    -0.06
    POSITIVE LOGITS
    ian
    0.10
    shire
    0.09
    ians
    0.08
     Academ
    0.08
    ization
    0.08
    à¥Ģय
    0.08
    sian
    0.08
    972
    0.07
    lot
    0.07
    s
    0.07
    Activations Density 0.003%

    No Known Activations