© 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. 60011
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and brackets

    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
    ursal
    -0.07
    idae
    -0.06
    cke
    -0.06
    agrid
    -0.06
    mares
    -0.06
    hev
    -0.06
    ropol
    -0.06
    erus
    -0.06
    ivia
    -0.06
    frica
    -0.06
    POSITIVE LOGITS
    (æĹ¥
    0.07
    Porno
    0.07
    .fd
    0.07
    Âłmiles
    0.06
    taÅŁ
    0.06
    uo
    0.06
    opleft
    0.06
    :init
    0.06
    âĹİ
    0.06
    VK
    0.06
    Activations Density 0.001%

    No Known Activations