© 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. 17-LLAMASCOPE-RES-131K
    11. 84717
    Prev
    Next
    INDEX
    Explanations

    references to environmental settings and 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
    877
    -0.06
    á»Ĩ
    -0.06
     culture
    -0.06
    434
    -0.06
    ancell
    -0.06
     surrounding
    -0.06
     pil
    -0.06
    984
    -0.06
    ious
    -0.06
    ousands
    -0.06
    POSITIVE LOGITS
    omial
    0.07
    ê½
    0.07
    InSection
    0.07
    _bundle
    0.07
    idar
    0.06
    eload
    0.06
    ocos
    0.06
    erva
    0.06
     ÑģÑĦ
    0.06
    loquent
    0.06
    Activations Density 0.003%

    No Known Activations