© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 93397
    Prev
    Next
    INDEX
    Explanations

    quantifiable conditions or limitations related to programs and agreements

    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
     klu
    -0.07
    otte
    -0.07
    lando
    -0.07
    ugins
    -0.07
    èĸ¦
    -0.07
    adero
    -0.07
    ader
    -0.07
    lingen
    -0.06
    reau
    -0.06
     ä¸ĵ
    -0.06
    POSITIVE LOGITS
     household
    0.07
    aks
    0.07
     /*#__
    0.07
     per
    0.06
    ties
    0.06
     maximum
    0.06
    maximum
    0.06
     limit
    0.06
     households
    0.06
    :max
    0.06
    Activations Density 0.005%

    No Known Activations