© 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. 55983
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and quotation-related phrases

    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
    ensburg
    -0.07
    olars
    -0.07
    uite
    -0.07
    erot
    -0.07
    roker
    -0.07
    SharedPointer
    -0.07
    ainless
    -0.07
    hipster
    -0.07
    ibox
    -0.07
    ongoose
    -0.07
    POSITIVE LOGITS
    amas
    0.06
    ou
    0.06
     customers
    0.06
     âĢı
    0.06
    .opens
    0.06
    -simple
    0.06
     Customers
    0.06
     customer
    0.06
    olia
    0.06
    åIJĽ
    0.06
    Activations Density 0.000%

    No Known Activations