© 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. 61473
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exclusivity or specific conditions related to access and eligibility

    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
    ÏģÏĩ
    -0.07
    BaÅŁ
    -0.07
     Bender
    -0.06
    izzy
    -0.06
     graduation
    -0.06
    semb
    -0.06
    excel
    -0.06
    ress
    -0.06
    nees
    -0.06
    ome
    -0.06
    POSITIVE LOGITS
     certain
    0.10
     Certain
    0.08
    urator
    0.07
    ä¸Ģç§į
    0.07
    Certain
    0.07
    within
    0.07
    ecom
    0.06
    åıªèĥ½
    0.06
     within
    0.06
     certains
    0.06
    Activations Density 0.025%

    No Known Activations