© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86137
    Prev
    Next
    INDEX
    Explanations

    phrases indicating growth or increase in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    etik
    -0.08
    baugh
    -0.07
     kê
    -0.07
     Sommer
    -0.07
    .Pointer
    -0.07
    csi
    -0.07
    OOM
    -0.07
     Král
    -0.07
    snippet
    -0.07
    expo
    -0.07
    POSITIVE LOGITS
    988
    0.07
    035
    0.07
    apl
    0.06
    (PyObject
    0.06
    ix
    0.06
     Kay
    0.06
    asm
    0.06
    985
    0.06
     McCl
    0.06
    erais
    0.05
    Activations Density 0.057%

    No Known Activations