© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 55407
    Prev
    Next
    INDEX
    Explanations

    complex interactions and nuanced relationships in various 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
    olum
    -0.07
         č↵
    -0.07
    à¹Īà¸Ńà¹Ħà¸Ľ
    -0.07
    بش
    -0.07
    ria
    -0.07
    umd
    -0.07
    ë¥
    -0.06
          č↵
    -0.06
    Ī
    -0.06
    urus
    -0.06
    POSITIVE LOGITS
     due
    0.22
     thanks
    0.19
    due
    0.19
     because
    0.16
    thanks
    0.16
     Due
    0.15
    because
    0.15
    çĶ±äºİ
    0.14
    Due
    0.14
    _due
    0.14
    Activations Density 0.274%

    No Known Activations