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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1715
    Prev
    Next
    INDEX
    Explanations

    references to social support systems and communities

    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
    acus
    -0.07
    ä¼ı
    -0.07
     Consort
    -0.07
    ладÑĥ
    -0.07
    ëĶ°
    -0.06
    ìĿ¸ìĿĺ
    -0.06
    mix
    -0.06
    VOKE
    -0.06
    oli
    -0.06
    еÑĢÑĤи
    -0.06
    POSITIVE LOGITS
     who
    0.17
     whom
    0.15
    who
    0.14
     whose
    0.13
    whose
    0.11
     kteÅĻÃŃ
    0.10
     qui
    0.09
     اÙĦØ°ÙĬÙĨ
    0.09
     quienes
    0.09
     Who
    0.08
    Activations Density 0.216%

    No Known Activations