© 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. 126814
    Prev
    Next
    INDEX
    Explanations

    phrases related to registration processes

    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
    aille
    -0.06
    acha
    -0.06
    illi
    -0.06
     (
    -0.06
    ,
    -0.06
    uro
    -0.06
    otto
    -0.06
    akh
    -0.06
     Sen
    -0.05
    aire
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    éħ
    0.08
    ospace
    0.07
    _globals
    0.07
    oleon
    0.07
    ãĥ¼ãĥ©
    0.07
    YLON
    0.07
     ìĿ´ëŁ¬
    0.07
    ÃĸL
    0.07
     dilig
    0.07
    Activations Density 0.010%

    No Known Activations