© 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. 99262
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to Oracle and VMware technologies

    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
    osa
    -0.07
    antt
    -0.07
    efe
    -0.07
    uso
    -0.07
     OTHERWISE
    -0.07
    udes
    -0.06
    peg
    -0.06
    agra
    -0.06
    azzo
    -0.06
    Td
    -0.06
    POSITIVE LOGITS
    اظ
    0.07
    CLU
    0.06
     critical
    0.06
     stabilization
    0.06
    _growth
    0.06
     stabil
    0.06
     Pis
    0.06
    isque
    0.06
    ļ
    0.06
    ilos
    0.06
    Activations Density 0.005%

    No Known Activations