© 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 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. 17-LLAMASCOPE-RES-131K
    11. 88361
    Prev
    Next
    INDEX
    Explanations

    references to physical or mathematical concepts, particularly those involving "the" in various 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
    BackPressed
    -0.07
    stad
    -0.06
     poil
    -0.06
    _perc
    -0.06
    оба
    -0.06
    omid
    -0.06
     kural
    -0.06
    é¢ĺ
    -0.06
     ÙĤدر
    -0.06
    é¡
    -0.06
    POSITIVE LOGITS
    sense
    0.08
    gart
    0.07
     Hv
    0.07
     case
    0.07
    eca
    0.07
    anner
    0.07
     context
    0.07
     range
    0.07
     meanwhile
    0.06
     literature
    0.06
    Activations Density 0.053%

    No Known Activations