© 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. 41141
    Prev
    Next
    INDEX
    Explanations

    formal references to official documents and meeting protocols

    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
    iban
    -0.06
     newX
    -0.06
    imators
    -0.06
    ansi
    -0.06
    hte
    -0.06
     newPos
    -0.06
    θο
    -0.06
    ehler
    -0.06
     Slee
    -0.06
    leigh
    -0.06
    POSITIVE LOGITS
    Nİ
    0.06
     clouds
    0.06
    lava
    0.06
    ุà¸Ĥ
    0.06
    AMA
    0.06
    .EventQueue
    0.06
    ายà¸Ļ
    0.06
    -await
    0.06
    .sale
    0.06
    descending
    0.06
    Activations Density 0.003%

    No Known Activations