© 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. 58172
    Prev
    Next
    INDEX
    Explanations

    patterns of punctuation and spacing, particularly in text formatting

    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
    jabi
    -0.09
     Müz
    -0.07
    LETTE
    -0.07
    culos
    -0.07
    lical
    -0.07
    achable
    -0.07
    bic
    -0.07
     اÙĦÙĨÙĪ
    -0.07
    ÑĪин
    -0.07
    Handled
    -0.07
    POSITIVE LOGITS
     end
    0.06
    asma
    0.06
    ardown
    0.05
     cgi
    0.05
    kest
    0.05
    ates
    0.05
    endas
    0.05
     wre
    0.05
     functions
    0.05
    enda
    0.05
    Activations Density 0.002%

    No Known Activations