© 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. 70610
    Prev
    Next
    INDEX
    Explanations

    references to physical sensations and conditions

    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
    reator
    -0.08
    rette
    -0.07
    åħį
    -0.07
    ÑĥÑĤи
    -0.07
    noch
    -0.07
    аÑĤок
    -0.07
    缮çļĦ
    -0.07
     Ñħод
    -0.06
    ì§ij
    -0.06
    æѦ
    -0.06
    POSITIVE LOGITS
     Rencontre
    0.06
     Garc
    0.06
     Kramer
    0.06
    ARB
    0.06
    angel
    0.06
    ãĥ¼ãĥľ
    0.05
     Accountability
    0.05
     vigil
    0.05
    ogi
    0.05
    æŁ´
    0.05
    Activations Density 0.001%

    No Known Activations