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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87632
    Prev
    Next
    INDEX
    Explanations

    references to the term "derived" and its variations in various contexts

    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
    eller
    -0.07
    iar
    -0.06
    ilo
    -0.06
    iser
    -0.06
    aise
    -0.06
     orthodox
    -0.06
    ylon
    -0.06
    NZ
    -0.06
    ellar
    -0.06
     Fixture
    -0.06
    POSITIVE LOGITS
    fts
    0.08
    neÄŁi
    0.07
    วà¸ģ
    0.07
    ény
    0.07
    .TabControl
    0.07
    krom
    0.07
    Å¡em
    0.07
    .spacing
    0.07
     Wong
    0.07
    بÙĪاسطة
    0.07
    Activations Density 0.037%

    No Known Activations