© 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. 15-LLAMASCOPE-RES-131K
    11. 88958
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially related to years and episode counts in a series

    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
    ··
    -0.07
    éŁ¿
    -0.07
    SSERT
    -0.06
    _hooks
    -0.06
    oyal
    -0.06
     Koch
    -0.06
     friction
    -0.06
    âĢ¦âĢ¦↵↵
    -0.06
    okia
    -0.06
     Meta
    -0.05
    POSITIVE LOGITS
    @nate
    0.08
    icmp
    0.07
    ADDE
    0.07
     اÙĦرÙħزÙĬØ©
    0.07
    idot
    0.07
    }elseif
    0.07
    556
    0.07
    dfa
    0.06
    ÐIJÑĢÑħÑĸв
    0.06
    Ð®ÐĽ
    0.06
    Activations Density 0.016%

    No Known Activations