© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89571
    Prev
    Next
    INDEX
    Explanations

    terms related to change, transformation, and entities

    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
    aeda
    -0.08
    loat
    -0.07
    pany
    -0.07
    onom
    -0.06
    ÑijÑĤ
    -0.06
    esi
    -0.06
    uml
    -0.06
    arger
    -0.06
    ume
    -0.06
    .cx
    -0.06
    POSITIVE LOGITS
     etc
    0.11
     ÑĤоÑīо
    0.08
    etc
    0.07
     perhaps
    0.07
     maybe
    0.07
    598
    0.07
    itt
    0.07
    оÑĤÑĮ
    0.07
    çŃī
    0.06
     ëĵ±ìĿĦ
    0.06
    Activations Density 0.061%

    No Known Activations