© 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. 87386
    Prev
    Next
    INDEX
    Explanations

    references to excessive quantities or amounts

    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
    shan
    -0.07
    elp
    -0.07
    ulously
    -0.07
    plug
    -0.07
    мелÑĮ
    -0.07
    inch
    -0.06
     Oc
    -0.06
    ickle
    -0.06
    oci
    -0.06
    orgot
    -0.06
    POSITIVE LOGITS
    alls
    0.08
    drive
    0.07
    tones
    0.07
    eview
    0.07
    lander
    0.07
    rende
    0.07
    hang
    0.07
    brero
    0.06
    lying
    0.06
    kill
    0.06
    Activations Density 0.024%

    No Known Activations