© 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. 125764
    Prev
    Next
    INDEX
    Explanations

    instances of output or print syntax in code

    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
    795
    -0.07
    urd
    -0.07
    ooks
    -0.07
    ivent
    -0.07
    ifest
    -0.06
    ien
    -0.06
    odega
    -0.06
    reste
    -0.06
    úsqueda
    -0.06
    ledon
    -0.06
    POSITIVE LOGITS
    aching
    0.08
    inz
    0.07
     SHARES
    0.07
    acen
    0.06
    ocs
    0.06
    æĿŁ
    0.06
    atcher
    0.06
    aving
    0.06
     REFER
    0.06
     endl
    0.06
    Activations Density 0.002%

    No Known Activations