© 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. 75458
    Prev
    Next
    INDEX
    Explanations

    references to prior actions or events described in a timeline

    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
    ÙģØ´
    -0.07
    old
    -0.07
    ris
    -0.07
    Ø©
    -0.07
    stan
    -0.07
    aud
    -0.07
    ening
    -0.07
    au
    -0.07
    eres
    -0.07
    urg
    -0.06
    POSITIVE LOGITS
     being
    0.12
    /post
    0.09
     Being
    0.07
    Being
    0.07
    being
    0.07
     publication
    0.07
     actual
    0.07
    że
    0.07
    usra
    0.07
    /at
    0.06
    Activations Density 0.012%

    No Known Activations