© 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 EvalsExportsinterp-engineNEWAPI 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. 42291
    Prev
    Next
    INDEX
    Explanations

    elements related to volcanic activity and its effects

    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
    dee
    -0.07
    ha
    -0.07
    alat
    -0.07
    æŃ²
    -0.07
    arios
    -0.06
    enberg
    -0.06
    DisplayStyle
    -0.06
     recess
    -0.06
    238
    -0.06
    oshi
    -0.06
    POSITIVE LOGITS
    .VisualBasic
    0.07
    leigh
    0.07
    __;
    0.07
     Rubin
    0.06
    æģ¯
    0.06
    oras
    0.06
    axon
    0.06
    notated
    0.06
    .AddParameter
    0.06
     göl
    0.06
    Activations Density 0.001%

    No Known Activations