© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 130888
    Prev
    Next
    INDEX
    Explanations

    quantifiers or terms indicating quantity

    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
    urdy
    -0.07
    ddit
    -0.07
    redit
    -0.07
    cxx
    -0.07
    aders
    -0.07
    cie
    -0.07
    _MAGIC
    -0.07
    itz
    -0.07
     Morrison
    -0.07
    опол
    -0.07
    POSITIVE LOGITS
    hetto
    0.08
     enough
    0.06
    ovit
    0.06
    791
    0.06
    uj
    0.06
    489
    0.06
    emma
    0.06
    ego
    0.06
    ief
    0.05
    aret
    0.05
    Activations Density 0.009%

    No Known Activations