© 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. 39881
    Prev
    Next
    INDEX
    Explanations

    descriptors related to genres or categories of creative works

    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
    itu
    -0.07
    ients
    -0.06
    olor
    -0.06
    ophage
    -0.06
    atorium
    -0.06
     Redistributions
    -0.06
    idi
    -0.06
    ace
    -0.06
    ISO
    -0.06
    .defineProperty
    -0.06
    POSITIVE LOGITS
     similar
    0.16
    similar
    0.14
     comparable
    0.13
     Similar
    0.13
     аналог
    0.13
    Similar
    0.13
    Comparable
    0.12
    akin
    0.12
     giá»ijng
    0.11
     simil
    0.11
    Activations Density 0.082%

    No Known Activations