© 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. 89745
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to public resources and their management

    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
    odon
    -0.09
    .scalablytyped
    -0.09
    pic
    -0.07
     Profiles
    -0.06
    /topics
    -0.06
     Liber
    -0.06
    endez
    -0.06
    olib
    -0.06
    enburg
    -0.06
    ÙĨز
    -0.06
    POSITIVE LOGITS
     пÑĢиÑħод
    0.07
    upe
    0.06
    uiten
    0.06
     fit
    0.06
     permanently
    0.06
    оÑĩ
    0.06
    _fit
    0.06
    _coverage
    0.06
    overlap
    0.06
    ëĿ½
    0.06
    Activations Density 0.166%

    No Known Activations