© 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. 60958
    Prev
    Next
    INDEX
    Explanations

    mentions of treasure hunt puzzles and related game mechanics

    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
    anship
    -0.07
    izards
    -0.07
    823
    -0.07
    άβ
    -0.07
     곧
    -0.06
    824
    -0.06
    opard
    -0.06
    izard
    -0.06
    845
    -0.06
     division
    -0.06
    POSITIVE LOGITS
    ä¼ı
    0.07
    .req
    0.07
    bear
    0.07
    _blueprint
    0.06
     Dialogue
    0.06
     Sloan
    0.06
    akk
    0.06
    iggs
    0.06
     collect
    0.06
     Harden
    0.06
    Activations Density 0.049%

    No Known Activations