© 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. 5-LLAMASCOPE-RES-131K
    11. 125684
    Prev
    Next
    INDEX
    Explanations

    references to guest posts and contributions in a blog or article context

    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
    rys
    -0.07
    ycl
    -0.07
    ases
    -0.07
    iro
    -0.06
    ena
    -0.06
    yc
    -0.06
    ategorized
    -0.06
    евиÑĩ
    -0.06
    iew
    -0.06
     Voy
    -0.06
    POSITIVE LOGITS
    acas
    0.07
    alim
    0.07
    æļ
    0.07
    imuth
    0.06
     TMPro
    0.06
    .vertx
    0.06
    ома
    0.06
    AtIndex
    0.06
    åŁ¹
    0.06
    ZA
    0.06
    Activations Density 0.004%

    No Known Activations