© 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. 9-LLAMASCOPE-RES-131K
    11. 95751
    Prev
    Next
    INDEX
    Explanations

    references to fictional universes and their respective elements

    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
    SED
    -0.06
    stral
    -0.06
    etten
    -0.06
    tvrt
    -0.06
    atische
    -0.06
    .GUI
    -0.06
    .ribbon
    -0.06
    sockopt
    -0.06
    ESIS
    -0.06
    /license
    -0.06
    POSITIVE LOGITS
    arth
    0.08
    yu
    0.07
    anik
    0.07
    olik
    0.06
    ulu
    0.06
    OfWork
    0.06
    hom
    0.06
    anova
    0.06
    Ark
    0.06
    ayd
    0.06
    Activations Density 0.001%

    No Known Activations