© 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. 38537
    Prev
    Next
    INDEX
    Explanations

    concepts related to rights and responsibilities in educational and social contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģ人
    -0.07
    aise
    -0.07
    Ñħа
    -0.07
    hoff
    -0.06
    opa
    -0.06
     âķ
    -0.06
    书记
    -0.06
    رÙĬر
    -0.06
    atik
    -0.06
    asy
    -0.06
    POSITIVE LOGITS
    éģ
    0.07
    alous
    0.07
     scr
    0.07
    avenport
    0.06
    nel
    0.06
     Kro
    0.06
    always
    0.06
     always
    0.06
     ALWAYS
    0.06
    idebar
    0.06
    Activations Density 0.020%

    No Known Activations