© 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. 16488
    Prev
    Next
    INDEX
    Explanations

    phrases describing dining options and experiences

    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
    å®
    -0.08
    inel
    -0.07
    åģ
    -0.07
    unken
    -0.07
    imon
    -0.07
    ungeon
    -0.07
    arella
    -0.07
    Ø¡
    -0.07
    chein
    -0.07
    reau
    -0.07
    POSITIVE LOGITS
     ORDER
    0.06
     ordered
    0.06
    ForObject
    0.06
     AG
    0.06
    ãĥ¼ãĥī
    0.06
     Trip
    0.06
    Ordered
    0.06
    AGMA
    0.06
     nailed
    0.06
     prelim
    0.05
    Activations Density 0.010%

    No Known Activations