© 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. 57315
    Prev
    Next
    INDEX
    Explanations

    references to publications or speeches and their associated dates

    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
    Portal
    -0.07
    оÑĢоз
    -0.07
     завеÑĢ
    -0.07
    lify
    -0.07
    é»
    -0.06
    ulumi
    -0.06
    ilan
    -0.06
    stances
    -0.06
    รม
    -0.06
    _SAFE
    -0.06
    POSITIVE LOGITS
     his
    0.09
     jego
    0.08
     zijn
    0.07
     seinen
    0.07
     ãĢĬ
    0.07
     suas
    0.07
     jeho
    0.07
     seu
    0.07
     его
    0.06
    ä»ĸçļĦ
    0.06
    Activations Density 0.026%

    No Known Activations