© 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. 29234
    Prev
    Next
    INDEX
    Explanations

    negations or instances of something being absent or not present

    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
     only
    -0.06
    only
    -0.06
     Inc
    -0.06
    hol
    -0.06
     loft
    -0.06
     dific
    -0.06
     magn
    -0.06
     blown
    -0.06
     ONLY
    -0.06
     difficulty
    -0.06
    POSITIVE LOGITS
     anymore
    0.08
    cu
    0.07
    rack
    0.07
     Daniels
    0.07
    aData
    0.06
    dük
    0.06
    kinson
    0.06
     Ler
    0.06
    invert
    0.06
    cona
    0.06
    Activations Density 0.020%

    No Known Activations