© 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. 77158
    Prev
    Next
    INDEX
    Explanations

    the word "are" and its variations in different 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
    stoup
    -0.09
    aries
    -0.08
    ajs
    -0.08
    ãĥ«ãĥĪ
    -0.08
    ä¸Ģ个
    -0.07
     pyt
    -0.07
    ạm
    -0.07
    ieres
    -0.07
    artin
    -0.07
    lyn
    -0.07
    POSITIVE LOGITS
     there
    0.08
    ady
    0.08
    /w
    0.08
    olas
    0.08
     certain
    0.07
     you
    0.07
    tha
    0.07
     all
    0.07
     it
    0.07
     these
    0.07
    Activations Density 0.017%

    No Known Activations