© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106272
    Prev
    Next
    INDEX
    Explanations

    references to numerical data or measurements in context

    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
    boa
    -0.07
    OSC
    -0.07
    isode
    -0.07
    elib
    -0.07
    edition
    -0.07
     Argument
    -0.07
    foy
    -0.07
    igure
    -0.07
    ãģĵãģĿ
    -0.07
    edl
    -0.06
    POSITIVE LOGITS
    antage
    0.06
     оÑĢганизма
    0.06
    ัà¸įà¸į
    0.06
    ynamo
    0.06
     Fletcher
    0.06
    271
    0.06
    anner
    0.05
    ë³´ìķĺëĭ¤
    0.05
    ders
    0.05
    273
    0.05
    Activations Density 0.028%

    No Known Activations