© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129477
    Prev
    Next
    INDEX
    Explanations

    references to celebrations and parties

    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
    ICAST
    -0.06
    опÑĢи
    -0.06
    TOTYPE
    -0.06
     conv
    -0.06
    359
    -0.06
     빨
    -0.06
     Pride
    -0.06
     IMPLIED
    -0.06
    ãĥ«ãĥķ
    -0.06
     terminal
    -0.06
    POSITIVE LOGITS
     reportedly
    0.09
     private
    0.08
    private
    0.07
     dap
    0.07
    party
    0.07
     parties
    0.07
    olu
    0.07
    Private
    0.07
    yar
    0.07
    ạn
    0.07
    Activations Density 0.004%

    No Known Activations