© 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. 99048
    Prev
    Next
    INDEX
    Explanations

    phrases related to achievements and recognition

    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
    amas
    -0.07
    üz
    -0.07
    å¾Ģ
    -0.07
    ihn
    -0.06
    lak
    -0.06
    court
    -0.06
    erator
    -0.06
    Fort
    -0.06
    YTE
    -0.06
     Courts
    -0.06
    POSITIVE LOGITS
     finally
    0.09
    finally
    0.08
    nv
    0.06
    ç»Īäºİ
    0.06
    aná
    0.06
     Finally
    0.06
     عÙħÙĦ
    0.06
    \:
    0.05
    loit
    0.05
     Sel
    0.05
    Activations Density 0.075%

    No Known Activations