© 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. 55690
    Prev
    Next
    INDEX
    Explanations

    the use of the phrase "on" in various contexts

    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
    ala
    -0.07
    ate
    -0.06
    asp
    -0.06
    aar
    -0.06
    982
    -0.06
    گاÙĨÛĮ
    -0.06
     Er
    -0.06
    ola
    -0.06
    789
    -0.05
    rij
    -0.05
    POSITIVE LOGITS
    á»ĩ
    0.07
    gesch
    0.07
    ımızı
    0.07
    -valu
    0.07
    AINS
    0.07
    uelles
    0.07
    ood
    0.07
    _resolver
    0.06
     nackt
    0.06
    ardin
    0.06
    Activations Density 0.036%

    No Known Activations