© 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. 31752
    Prev
    Next
    INDEX
    Explanations

    terms related to anatomical or biological indentations and formations

    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
     rotterdam
    -0.07
    yard
    -0.07
    amburger
    -0.07
    shed
    -0.07
    endi
    -0.07
    価
    -0.06
     веÑīеÑģÑĤв
    -0.06
    ott
    -0.06
    .communication
    -0.06
    agrant
    -0.06
    POSITIVE LOGITS
     recess
    0.08
     alc
    0.06
     flush
    0.06
    -mounted
    0.06
    ionale
    0.06
    å¼ı
    0.06
    alc
    0.06
     pocket
    0.06
    ional
    0.06
    acon
    0.06
    Activations Density 0.003%

    No Known Activations