© 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. 69828
    Prev
    Next
    INDEX
    Explanations

    quantifiers and descriptive terms that indicate quantity or significance

    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
     which
    -0.07
     when
    -0.06
     should
    -0.06
    omen
    -0.06
    .arraycopy
    -0.06
     McKay
    -0.06
    ici
    -0.06
     with
    -0.06
    apons
    -0.06
    ãģ¤
    -0.06
    POSITIVE LOGITS
     exception
    0.09
    lac
    0.09
    being
    0.09
    nave
    0.08
    á»IJ
    0.08
     regard
    0.08
    standing
    0.08
     hindsight
    0.07
    ottle
    0.07
    aliz
    0.07
    Activations Density 0.039%

    No Known Activations