© 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. 129433
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and their corresponding properties

    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
    ÛĢ
    -0.08
    gency
    -0.07
    .biz
    -0.07
    ãģ£ãģ
    -0.07
    Allocator
    -0.07
    _Parse
    -0.07
    cil
    -0.07
    ÑģпÑĸлÑĮ
    -0.07
    Schedulers
    -0.07
    ãĥ³ãĥķ
    -0.07
    POSITIVE LOGITS
    /=
    0.07
     neither
    0.06
    aight
    0.06
    ingle
    0.06
    olate
    0.06
    /is
    0.06
     chant
    0.05
    oles
    0.05
     accident
    0.05
    ÑĭÑģ
    0.05
    Activations Density 0.192%

    No Known Activations