© 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. 63003
    Prev
    Next
    INDEX
    Explanations

    superlative descriptors or phrases indicating significance

    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
    áp
    -0.08
    à¸Ńà¸ĩà¸Īาà¸ģ
    -0.08
    .setter
    -0.08
     segundos
    -0.07
    quential
    -0.07
    	Copyright
    -0.07
    ÑĪев
    -0.07
    овиÑĩ
    -0.07
     lá»
    -0.07
    avaÅŁ
    -0.07
    POSITIVE LOGITS
     reason
    0.08
    483
    0.07
     major
    0.06
     recent
    0.06
    ,
    0.06
     only
    0.06
     that
    0.06
     key
    0.06
     earliest
    0.06
     recently
    0.06
    Activations Density 0.013%

    No Known Activations