© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 130086
    Prev
    Next
    INDEX
    Explanations

    uppercase letters and character sequences related to protocol or programming syntax

    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
    abled
    -0.07
    Composition
    -0.07
    @testable
    -0.06
    ecal
    -0.06
    (&(
    -0.06
    keit
    -0.06
     Steele
    -0.06
     compositions
    -0.06
     Cv
    -0.06
    öz
    -0.06
    POSITIVE LOGITS
    racat
    0.07
    .RunWith
    0.07
    Äł
    0.07
    uitka
    0.07
    åĦĢ
    0.07
     gratuites
    0.07
    atsapp
    0.07
    fel
    0.06
    âķĿ
    0.06
    endcode
    0.06
    Activations Density 0.000%

    No Known Activations