© 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. 55608
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of endings and continuations

    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
     kar
    -0.06
     bas
    -0.06
    lich
    -0.06
    inky
    -0.06
     Girls
    -0.05
    iren
    -0.05
     Ray
    -0.05
    Enlarge
    -0.05
    utral
    -0.05
    ानस
    -0.05
    POSITIVE LOGITS
    à¹ģà¸Ħ
    0.08
    éĻIJ
    0.08
     mere
    0.07
     merely
    0.07
    ĸ
    0.07
    793
    0.07
    bounded
    0.07
     limited
    0.07
    eldorf
    0.07
     solely
    0.07
    Activations Density 0.003%

    No Known Activations