© 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. 87450
    Prev
    Next
    INDEX
    Explanations

    references to business expansion and international networking

    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
    átka
    -0.07
    iple
    -0.06
     GUID
    -0.06
    iag
    -0.06
    ftype
    -0.06
    CUR
    -0.06
    hong
    -0.06
    eson
    -0.06
     navr
    -0.06
    Raises
    -0.06
    POSITIVE LOGITS
     regional
    0.09
     region
    0.08
     local
    0.07
     lokal
    0.07
     Clients
    0.07
     clients
    0.06
    Clients
    0.06
     bölge
    0.06
     Regional
    0.06
     additional
    0.06
    Activations Density 0.020%

    No Known Activations