© 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. 15-LLAMASCOPE-RES-131K
    11. 27532
    Prev
    Next
    INDEX
    Explanations

    references to discussions or dialogues involving a group or collective "we."

    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
    agan
    -0.07
    arkin
    -0.07
    otate
    -0.07
    å¾ĭ
    -0.06
    uguay
    -0.06
    ago
    -0.06
    beth
    -0.06
    616
    -0.06
    oui
    -0.06
    bero
    -0.06
    POSITIVE LOGITS
    uled
    0.07
     اÙĦرÙĬاض
    0.07
    ãĥ³ãĥķ
    0.07
    ibile
    0.07
    351
    0.06
     równ
    0.06
    _MPI
    0.06
    .Pow
    0.06
    Tracking
    0.06
    */}↵
    0.06
    Activations Density 0.013%

    No Known Activations