© 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. 125794
    Prev
    Next
    INDEX
    Explanations

    periods and punctuation marks that signify sentence endings

    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
    ias
    -0.06
    añ
    -0.06
    arten
    -0.06
    áb
    -0.06
    993
    -0.06
     Prot
    -0.06
    agra
    -0.06
    icies
    -0.06
    seau
    -0.06
    _ET
    -0.06
    POSITIVE LOGITS
    rog
    0.07
     tÃŃn
    0.06
    izzo
    0.06
    Як
    0.06
    efore
    0.06
     hed
    0.06
    essian
    0.06
    cov
    0.06
     newInstance
    0.06
    ãĥ«ãĥĪ
    0.06
    Activations Density 0.011%

    No Known Activations