© 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. 71716
    Prev
    Next
    INDEX
    Explanations

    words related to various subjects or categories that can be grouped together

    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
    107
    -0.07
    ãĥ³ãĥ
    -0.06
     både
    -0.06
     sach
    -0.06
    ling
    -0.06
    زاÙħ
    -0.06
    kus
    -0.06
     ones
    -0.06
    ptions
    -0.06
    luž
    -0.06
    POSITIVE LOGITS
     alike
    0.13
    /or
    0.09
    /etc
    0.08
    ythe
    0.07
    ARSE
    0.07
    iban
    0.07
    createForm
    0.07
    ellan
    0.07
     forms
    0.07
    ija
    0.07
    Activations Density 0.021%

    No Known Activations