© 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. 29469
    Prev
    Next
    INDEX
    Explanations

    labels and sections typically found in a table of contents or index, indicating the structure of a document

    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
    stown
    -0.07
    mitted
    -0.06
    ýt
    -0.06
     undo
    -0.06
    erspective
    -0.06
    itecture
    -0.06
    vers
    -0.06
    eting
    -0.05
    éo
    -0.05
     \"
    -0.05
    POSITIVE LOGITS
    аÑĢод
    0.07
    ofire
    0.06
    uxe
    0.06
    leans
    0.06
    INTR
    0.06
     ëĭ
    0.06
     Ill
    0.06
    _CSR
    0.06
     âĸ¼
    0.06
    ORIES
    0.06
    Activations Density 0.003%

    No Known Activations