© 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. 9-LLAMASCOPE-RES-131K
    11. 97599
    Prev
    Next
    INDEX
    Explanations

    references to Sufism and its spiritual leaders

    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
    ota
    -0.08
    anka
    -0.07
    ulkan
    -0.07
    éļĽ
    -0.07
    clone
    -0.07
    itm
    -0.07
    iap
    -0.07
    ypical
    -0.07
    覧
    -0.06
    arra
    -0.06
    POSITIVE LOGITS
    OfMonth
    0.06
     li
    0.06
    atism
    0.06
    $MESS
    0.05
    ynom
    0.05
     thought
    0.05
    ril
    0.05
    åĭĴ
    0.05
     passe
    0.05
     bon
    0.05
    Activations Density 0.008%

    No Known Activations