© 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. 87918
    Prev
    Next
    INDEX
    Explanations

    the first-person perspective in technical queries or issues

    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
    onta
    -0.07
    /raw
    -0.06
    uber
    -0.06
     Intersection
    -0.06
    جÙĦ
    -0.06
    оваÑĢ
    -0.06
     Pearce
    -0.06
    irst
    -0.06
     Germ
    -0.06
    ØŃÙĬ
    -0.06
    POSITIVE LOGITS
    407
    0.08
     recently
    0.08
    AMB
    0.07
     lately
    0.07
    alet
    0.07
     Recently
    0.07
     attempting
    0.06
    PKG
    0.06
    Æ¡i
    0.06
    üven
    0.06
    Activations Density 0.011%

    No Known Activations