© 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. 126057
    Prev
    Next
    INDEX
    Explanations

    phrases related to best practices and standards in medical science

    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
    .isBlank
    -0.06
    _guide
    -0.06
    ulas
    -0.06
     dzie
    -0.06
    817
    -0.06
    805
    -0.06
    _recursive
    -0.05
    055
    -0.05
    nes
    -0.05
     admins
    -0.05
    POSITIVE LOGITS
    iver
    0.08
    hopefully
    0.07
    ARAM
    0.07
    好äºĨ
    0.07
    igger
    0.07
    ìĬ¤íħĮ
    0.07
    øj
    0.07
    UPPORTED
    0.07
    ìĿ´ìĬĪ
    0.06
    (Table
    0.06
    Activations Density 0.000%

    No Known Activations