© 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. 9-LLAMASCOPE-RES-131K
    11. 93959
    Prev
    Next
    INDEX
    Explanations

    phrases indicating limitations or constraints

    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
    iola
    -0.08
    nez
    -0.07
    lsa
    -0.07
    ertility
    -0.06
    wil
    -0.06
    ElapsedTime
    -0.06
    ÅĻez
    -0.06
    eÄį
    -0.06
    ìĿ´ìĸ´
    -0.06
    .EventQueue
    -0.06
    POSITIVE LOGITS
     Conor
    0.07
    997
    0.07
    ippi
    0.07
    å°ĸ
    0.07
    oeff
    0.06
     GANG
    0.06
     Gang
    0.06
     managing
    0.06
    nip
    0.06
    .syntax
    0.06
    Activations Density 0.167%

    No Known Activations