© 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. 17-LLAMASCOPE-RES-131K
    11. 69089
    Prev
    Next
    INDEX
    Explanations

    terms related to tympanic membranes and medical evaluations

    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
     suck
    -0.06
     Fior
    -0.06
    unde
    -0.06
     interracial
    -0.06
    umba
    -0.06
    _INTERRUPT
    -0.06
    ayers
    -0.06
    ardi
    -0.06
     juices
    -0.06
    oint
    -0.06
    POSITIVE LOGITS
     hearing
    0.14
     Hearing
    0.14
     ear
    0.13
     coch
    0.13
     Ear
    0.13
     deaf
    0.13
    èĢ³
    0.11
    Ear
    0.11
     ÑģлÑĥÑħ
    0.11
    èģ
    0.10
    Activations Density 0.049%

    No Known Activations