© 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. 83750
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency in text

    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
    647
    -0.07
     Forum
    -0.06
    UNC
    -0.06
    ÄĮesk
    -0.06
    ymph
    -0.06
    iap
    -0.06
     Uniform
    -0.06
    Sdk
    -0.06
    udy
    -0.06
    Shown
    -0.06
    POSITIVE LOGITS
    볨
    0.07
    äº
    0.07
    swick
    0.07
    atsu
    0.07
    oksen
    0.07
    ulle
    0.06
    adge
    0.06
    antom
    0.06
    ÏģεÏĤ
    0.06
    .='
    0.06
    Activations Density 0.006%

    No Known Activations