© 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. 1954
    Prev
    Next
    INDEX
    Explanations

    elements related to nature and transcendent experiences

    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
    ritz
    -0.07
    utm
    -0.07
    ques
    -0.06
    ous
    -0.06
     Sob
    -0.06
    oman
    -0.06
    odem
    -0.06
    inary
    -0.06
    rab
    -0.06
    iber
    -0.06
    POSITIVE LOGITS
    úsqueda
    0.07
     batt
    0.07
     familiar
    0.07
     Huck
    0.07
    aney
    0.07
    issen
    0.07
    üc
    0.07
    (Cs
    0.06
    .Atomic
    0.06
    arness
    0.06
    Activations Density 0.082%

    No Known Activations