© 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. 40940
    Prev
    Next
    INDEX
    Explanations

    HTML and metadata elements related to web resources

    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
    aley
    -0.07
    veh
    -0.06
    quet
    -0.06
     yat
    -0.06
     Tao
    -0.05
    olis
    -0.05
    ware
    -0.05
    anut
    -0.05
    uye
    -0.05
     nuis
    -0.05
    POSITIVE LOGITS
    .rdf
    0.08
     åĸ
    0.07
    ÑĢез
    0.07
    uç
    0.07
    IfExists
    0.07
    iÄħ
    0.06
    rdf
    0.06
    geç
    0.06
    claimer
    0.06
    UCKET
    0.06
    Activations Density 0.002%

    No Known Activations