© 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. 74955
    Prev
    Next
    INDEX
    Explanations

    references to treasure and treasure-related concepts

    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
    soever
    -0.08
    allet
    -0.07
    otope
    -0.07
    íıŃ
    -0.07
    ãĥ³ãĥij
    -0.07
    zial
    -0.06
    _charset
    -0.06
    ripp
    -0.06
    skirts
    -0.06
    nar
    -0.06
    POSITIVE LOGITS
    ably
    0.07
     Chest
    0.07
    oard
    0.07
    lijk
    0.07
    ĶåĽŀ
    0.07
     tro
    0.07
    blink
    0.07
    ë¡ľìļ´
    0.07
    ment
    0.07
    chest
    0.07
    Activations Density 0.005%

    No Known Activations