© 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. 87404
    Prev
    Next
    INDEX
    Explanations

    references to dates and updates in articles

    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
    Ñħо
    -0.06
    ĵ¨
    -0.06
    lew
    -0.05
     rejuven
    -0.05
    os
    -0.05
    issing
    -0.05
     nghi
    -0.05
    ï
    -0.05
    رÙĪس
    -0.05
    eries
    -0.05
    POSITIVE LOGITS
    ampo
    0.07
    orrect
    0.07
    uba
    0.07
    /chart
    0.07
    TOTYPE
    0.07
    ICODE
    0.07
    accur
    0.07
    .MixedReality
    0.07
     addCriterion
    0.07
     udp
    0.07
    Activations Density 0.004%

    No Known Activations