© 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 EvalsExportsinterp-engineNEWAPI 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. 94866
    Prev
    Next
    INDEX
    Explanations

    comparative phrases involving the word "than."

    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
    usercontent
    -0.09
    erten
    -0.09
    gaard
    -0.08
    ừ
    -0.08
    á»ħ
    -0.08
    ingt
    -0.08
    ạ
    -0.08
    ÑĨей
    -0.08
    ptal
    -0.08
    âĢ¦"↵↵
    -0.07
    POSITIVE LOGITS
     ever
    0.09
     usual
    0.07
     the
    0.07
     those
    0.07
     any
    0.07
    -ever
    0.07
     what
    0.06
    a
    0.06
     meets
    0.06
    issa
    0.06
    Activations Density 0.082%

    No Known Activations