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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117808
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "new" in code-related contexts

    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
    oldt
    -0.08
    æ¡ĥ
    -0.08
    zar
    -0.07
    опол
    -0.07
    IGH
    -0.07
    oble
    -0.07
    wnd
    -0.07
    uien
    -0.07
    ç«ł
    -0.07
    ystone
    -0.07
    POSITIVE LOGITS
    .Arguments
    0.06
     inst
    0.06
    otomy
    0.06
     Pill
    0.05
     Animalia
    0.05
    enties
    0.05
    emap
    0.05
     woven
    0.05
    åħĥ
    0.05
     Ding
    0.05
    Activations Density 0.003%

    No Known Activations