© 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. 103462
    Prev
    Next
    INDEX
    Explanations

    numerical timestamps or sequences related to time

    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
    براÛĮ
    -0.07
    .Apis
    -0.07
    imas
    -0.06
     Boo
    -0.06
    pj
    -0.06
     Mastery
    -0.06
    elu
    -0.06
     antic
    -0.06
    اخ
    -0.06
    oslav
    -0.06
    POSITIVE LOGITS
    swer
    0.07
    oui
    0.07
    koli
    0.07
    openh
    0.07
     Gow
    0.06
    EH
    0.06
    ilde
    0.06
     dw
    0.06
    ê³
    0.06
    ÙĪع
    0.06
    Activations Density 0.000%

    No Known Activations