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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78797
    Prev
    Next
    INDEX
    Explanations

    mathematical notation related to sequences and functions

    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
    (es
    -0.07
    oller
    -0.07
    ugen
    -0.06
    oh
    -0.06
    ussian
    -0.06
    ugg
    -0.06
     Lands
    -0.06
    ä½Ļ
    -0.06
     Gunn
    -0.06
    ussen
    -0.06
    POSITIVE LOGITS
    -fontawesome
    0.07
     cons
    0.07
    èĬĻ
    0.07
     Destruction
    0.07
    .unpack
    0.07
    /plugin
    0.07
    iddi
    0.06
     tieten
    0.06
     Cups
    0.06
    eria
    0.06
    Activations Density 0.065%

    No Known Activations