© 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. 27521
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical data transmission and management

    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
     Asi
    -0.07
    yal
    -0.07
    (ID
    -0.06
    âĦ
    -0.06
    uest
    -0.06
     congest
    -0.06
    EA
    -0.06
    erged
    -0.05
    enes
    -0.05
     zab
    -0.05
    POSITIVE LOGITS
    //{{
    0.07
     FIXME
    0.07
    utsch
    0.07
    stadt
    0.07
    unte
    0.07
    swer
    0.07
    untu
    0.07
    hetto
    0.06
    /simple
    0.06
    swers
    0.06
    Activations Density 0.004%

    No Known Activations