© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76918
    Prev
    Next
    INDEX
    Explanations

    tab-related commands or symbols

    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
     ÙĨب
    -0.06
    kara
    -0.06
    auss
    -0.06
    KT
    -0.06
    stry
    -0.06
    (IServiceCollection
    -0.06
    argon
    -0.06
    argent
    -0.06
    _hierarchy
    -0.06
     corre
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĤ¬
    0.07
    ueil
    0.07
    ayout
    0.07
    ycz
    0.06
    ustain
    0.06
    Leap
    0.06
    αι
    0.06
    :length
    0.06
    å¼¾
    0.06
    ë¹ĦìķĦ
    0.06
    Activations Density 0.000%

    No Known Activations